© 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. 33-TRANSCODER-HP
    7. 53503
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (country
    -0.30
    ppy
    -0.27
    province
    -0.27
    å¸ĿåĽ½
    -0.27
    åħ¨åĽ½
    -0.26
    åĽ½åľŁ
    -0.26
    ç¾İåĽ½
    -0.26
    _attached
    -0.26
     province
    -0.25
     country
    -0.25
    POSITIVE LOGITS
     In
    0.35
    In
    0.34
    _in
    0.32
    in
    0.31
     Sc
    0.31
    -in
    0.31
     sc
    0.30
     IN
    0.30
    .getIn
    0.28
     invers
    0.27
    Activations Density 0.019%

    No Known Activations