© 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. 25-TRANSCODER-HP
    7. 108591
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    han
    -0.27
    arket
    -0.26
    urent
    -0.26
     insiders
    -0.26
    ingles
    -0.26
     germ
    -0.25
    ombine
    -0.24
    æ¦Ń
    -0.24
     archive
    -0.24
    uper
    -0.24
    POSITIVE LOGITS
    ä¸Ģä¸ĸ
    0.27
    iad
    0.26
     favicon
    0.25
    æľ¨è´¨
    0.24
    _block
    0.24
    enÃŃ
    0.24
     presum
    0.24
    æį¢
    0.23
    åħ¥åѦ
    0.23
    ICODE
    0.23
    Activations Density 0.897%

    No Known Activations

    This feature has no known activations.