© 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. 8813
    Prev
    Next
    INDEX
    Explanations

    for

    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
    U
    -0.07
     getX
    -0.07
     acid
    -0.07
    .legend
    -0.07
     المختلف
    -0.07
     volatile
    -0.07
    ющим
    -0.07
    镐
    -0.07
    聽
    -0.07
    <Vertex
    -0.06
    POSITIVE LOGITS
     donate
    0.08
    _thresh
    0.07
    ccount
    0.07
     tied
    0.07
     respons
    0.07
     nicknamed
    0.07
    鼷
    0.07
    Unmount
    0.07
     instit
    0.07
    nection
    0.06
    Activations Density 0.002%

    No Known Activations