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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40121
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    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
    阻
    -0.07
    ennon
    -0.07
    リン
    -0.07
    ノー
    -0.06
    겐
    -0.06
    меща
    -0.06
    ᴸ
    -0.06
     Sharing
    -0.06
    镁
    -0.06
    _effects
    -0.06
    POSITIVE LOGITS
     ---------
    0.08
    ulnerable
    0.07
     createdAt
    0.07
    悼
    0.07
     wf
    0.07
    wife
    0.07
     documento
    0.06
    اة
    0.06
    Monthly
    0.06
     При
    0.06
    Activations Density 0.005%

    No Known Activations