© 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. 39710
    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
    oque
    -0.31
     First
    -0.28
    imensional
    -0.28
    å¹²éĥ¨
    -0.27
    åıĺå¾Ĺ
    -0.26
     immune
    -0.26
    unders
    -0.26
    uilt
    -0.26
     e
    -0.25
    end
    -0.25
    POSITIVE LOGITS
    ENER
    0.31
    tÃł
    0.28
    é¢ĦæĬ¥
    0.27
    tsy
    0.27
    ETF
    0.26
    ANA
    0.26
     hôn
    0.26
    EXPECTED
    0.25
     EURO
    0.25
     snatch
    0.25
    Activations Density 0.074%

    No Known Activations

    This feature has no known activations.