© 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. 35-TRANSCODER-HP
    7. 39591
    Prev
    Next
    INDEX
    Explanations

    Pre

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     silicon
    -0.31
     Stations
    -0.27
     arithmetic
    -0.27
     S
    -0.26
     Silicon
    -0.26
     ganze
    -0.26
     intern
    -0.26
     Te
    -0.26
    _S
    -0.26
     these
    -0.25
    POSITIVE LOGITS
    affen
    0.34
    ialis
    0.33
    ALSE
    0.31
    psc
    0.31
    PRS
    0.30
    togroup
    0.30
    lse
    0.30
    resher
    0.29
    POSE
    0.29
    pla
    0.29
    Activations Density 0.074%

    No Known Activations