© 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. 19-RESID-POST-AA
    11. 69414
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CT
    -0.07
    %).↵↵
    -0.07
     Киев
    -0.07
    {}↵↵
    -0.07
     signifies
    -0.07
    自来
    -0.07
    荜
    -0.07
     מסו
    -0.07
    (Op
    -0.06
     Vo
    -0.06
    POSITIVE LOGITS
     функци
    0.07
    RPC
    0.07
    處理
    0.07
    蝴蝶
    0.06
     regress
    0.06
    ="",
    0.06
    getParam
    0.06
    _AdjustorThunk
    0.06
     revers
    0.06
     messed
    0.06
    Activations Density 0.057%

    No Known Activations