© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80656
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    reader-submitted questions to advice/expert columns, especially salutations and first-person problem descriptions addressed to a named recipient.

    oai_token-act-pair · gpt-5
    Triggered 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
    Negative Logits
     dra
    -0.08
    CSI
    -0.06
    פגישה
    -0.06
    EqualTo
    -0.06
     advisers
    -0.06
    crm
    -0.06
    _processes
    -0.06
    与时
    -0.06
    ляет
    -0.06
    עונה
    -0.06
    POSITIVE LOGITS
     đơn
    0.07
    chema
    0.07
     المجلس
    0.07
    >[]
    0.07
    🏘
    0.07
     만들
    0.06
    肠
    0.06
     expl
    0.06
     spikes
    0.06
    @Enable
    0.06
    Activations Density 0.034%

    No Known Activations