© 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. 39439
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çIJĨä¼ļ
    -0.26
     intrigue
    -0.26
    begin
    -0.25
     Bears
    -0.24
    æĿĻ
    -0.24
    .begin
    -0.24
    starter
    -0.24
     Dome
    -0.23
    Å¡e
    -0.23
    sharp
    -0.23
    POSITIVE LOGITS
    اء
    0.29
    lé
    0.26
    Eu
    0.26
     EEPROM
    0.25
    centers
    0.25
    cased
    0.25
    aling
    0.25
     customized
    0.25
    ãĥ³ãĤ°
    0.24
    ativas
    0.24
    Activations Density 56.596%

    No Known Activations

    This feature has no known activations.