© 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. 76034
    Prev
    Next
    INDEX
    Explanations

    teaching/selling something

    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
    _finder
    -0.08
    回落
    -0.08
    nia
    -0.08
    notify
    -0.07
    Balance
    -0.07
    هم
    -0.07
     novice
    -0.07
    牌照
    -0.06
     нам
    -0.06
     lag
    -0.06
    POSITIVE LOGITS
    ?↵↵↵↵
    0.08
    \Resources
    0.07
     anticipated
    0.07
     ambitions
    0.07
    }↵↵
    0.07
    .’”↵↵
    0.07
    失
    0.07
    決
    0.07
    궜
    0.07
     sequel
    0.07
    Activations Density 0.130%

    No Known Activations