© 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. 39151
    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
    ä¸ĢåıĮ
    -0.28
    _cur
    -0.26
    jerne
    -0.25
    æĢ¥
    -0.24
    Bear
    -0.24
    è¿Ļæī¹
    -0.24
    ipers
    -0.24
    -pin
    -0.24
    ercial
    -0.23
    idable
    -0.23
    POSITIVE LOGITS
    edException
    0.27
     Nou
    0.27
     wre
    0.25
     millennium
    0.25
     Bols
    0.24
    _NE
    0.24
    prs
    0.24
    enko
    0.24
     latter
    0.23
    è¯Ŀè¯Ń
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.