© 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. 39787
    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
    两æĿ¡
    -0.31
    éģ¿
    -0.28
    rette
    -0.28
    ä¸ĢæĿ¡
    -0.27
    è¿Ļ两个
    -0.27
    ä¸īæĿ¡
    -0.27
    OK
    -0.26
    è°ĥ
    -0.25
    arity
    -0.25
    eto
    -0.25
    POSITIVE LOGITS
    oom
    0.30
    imeline
    0.28
     coherent
    0.25
    icc
    0.25
    `č↵
    0.24
    uft
    0.24
    omics
    0.24
     depict
    0.24
    ween
    0.24
    çľĭèijĹ
    0.24
    Activations Density 0.068%

    No Known Activations

    This feature has no known activations.