© 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. 39967
    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
    dux
    -0.26
    EDIA
    -0.26
     fair
    -0.26
    ayload
    -0.25
    æĢ»ä¼ļ
    -0.25
     few
    -0.24
    arsity
    -0.24
    èĥ½æ»¡è¶³
    -0.24
    tracted
    -0.24
    aravel
    -0.23
    POSITIVE LOGITS
    .createFrom
    0.30
     ..."
    0.28
     pointed
    0.27
    à¸ķà¸Ļà¹Ģà¸Ńà¸ĩ
    0.27
    aina
    0.26
     pops
    0.24
     ...č↵
    0.24
     ..."↵↵
    0.24
     ..."↵
    0.24
    poster
    0.23
    Activations Density 11.260%

    No Known Activations

    This feature has no known activations.