© 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. 68942
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific contexts

    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
     Warner
    -0.08
     }).
    -0.07
    _added
    -0.07
     GridView
    -0.07
     vmax
    -0.07
     stop
    -0.07
    .us
    -0.07
    ıdır
    -0.06
    万达
    -0.06
    ここまで
    -0.06
    POSITIVE LOGITS
     constructive
    0.09
    \Service
    0.07
    _paper
    0.07
    gran
    0.07
    具有良好
    0.07
    �
    0.07
     cheap
    0.06
    为人
    0.06
    -ip
    0.06
    做人
    0.06
    Activations Density 0.083%

    No Known Activations