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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 110377
    Prev
    Next
    INDEX
    Explanations

    people

    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
    ón
    -0.07
    agon
    -0.07
     Hurricanes
    -0.07
    });↵↵
    -0.06
     Раз
    -0.06
    の大
    -0.06
     curtains
    -0.06
    決定
    -0.06
    eson
    -0.06
     Rays
    -0.06
    POSITIVE LOGITS
     scipy
    0.07
    LIBINT
    0.07
    典雅
    0.06
    ┸
    0.06
    DIG
    0.06
    🆖
    0.06
    -plugin
    0.06
     zie
    0.06
    总的
    0.06
    供大家
    0.06
    Activations Density 0.000%

    No Known Activations