© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 71157
    Prev
    Next
    INDEX
    Explanations

    Detects mentions of typical/normal levels or quantitative norms—statements giving standard/expected amounts or measurements (often in the context of infant crying).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    direction
    -0.08
     clinical
    -0.07
     scient
    -0.07
     التي
    -0.07
     Calories
    -0.07
    )$
    -0.07
    DOI
    -0.07
     Hospital
    -0.07
    个国家
    -0.06
    onom
    -0.06
    POSITIVE LOGITS
    楽しめる
    0.07
    应付
    0.07
     Дмитр
    0.07
    _MUTEX
    0.07
     fundamentals
    0.07
    trzym
    0.07
    短期
    0.07
    셨
    0.07
    デザイン
    0.07
    frog
    0.07
    Activations Density 0.072%

    No Known Activations