© 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. 40012
    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
    äºĴ缸
    -0.31
    é¡¿
    -0.28
    TON
    -0.27
    alon
    -0.26
    éĹ²ç½®
    -0.26
    ton
    -0.25
    ä¸ĩåįĥ
    -0.25
    ç¾İé£Ł
    -0.24
    adal
    -0.24
    è¿«
    -0.24
    POSITIVE LOGITS
     sure
    0.29
    elib
    0.29
     enough
    0.28
    ocl
    0.27
    izable
    0.27
     necessary
    0.25
    lib
    0.25
     his
    0.25
     reliable
    0.25
     Eighth
    0.24
    Activations Density 3.775%

    No Known Activations

    This feature has no known activations.