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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19213
    Prev
    Next
    INDEX
    Explanations

    Leadership positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASTER
    -0.26
    esda
    -0.25
    sed
    -0.25
     Vinyl
    -0.25
    trs
    -0.25
    ç¬ĭ
    -0.25
    acs
    -0.24
    aps
    -0.24
     Ibn
    -0.24
    _BINDING
    -0.24
    POSITIVE LOGITS
    è²»
    0.30
     prop
    0.29
    iali
    0.29
    atic
    0.28
    prop
    0.27
     Prop
    0.27
    lic
    0.27
    æĭĵ
    0.27
    etic
    0.27
    ,alpha
    0.27
    Activations Density 1.398%

    No Known Activations