© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 90157
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     hei
    -0.34
    ä¸į好æĦıæĢĿ
    -0.27
    оÑģÑĤи
    -0.26
    öt
    -0.26
    æĬ¤
    -0.25
    /fixtures
    -0.25
    axter
    -0.25
    beg
    -0.24
    utar
    -0.24
    (MediaType
    -0.24
    POSITIVE LOGITS
    æ·Ģ
    0.27
    éĴ¤
    0.26
    *pow
    0.26
    à¸Ľà¸ģà¸Ħรà¸Ńà¸ĩ
    0.26
    stick
    0.25
    ä¿¡ç®±
    0.25
    ************************************************************************
    0.25
    wan
    0.25
    çħĮ
    0.25
    è¿Ļä¹Ī说
    0.25
    Activations Density 11.002%

    No Known Activations

    This feature has no known activations.