© 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. 88184
    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
    eding
    -0.28
    posted
    -0.25
    á»ģn
    -0.25
     Mov
    -0.24
    éªĮ
    -0.24
     Beds
    -0.24
    rics
    -0.24
     Eyl
    -0.24
    ilo
    -0.24
     delim
    -0.23
    POSITIVE LOGITS
    TokenType
    0.28
    .cloudflare
    0.26
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.25
    .house
    0.25
    (origin
    0.25
     обÑĢаÑī
    0.25
    å«¡
    0.25
    个åŁİå¸Ĥ
    0.25
    ä¸ĩåħ¬éĩĮ
    0.24
    ocity
    0.24
    Activations Density 10.893%

    No Known Activations

    This feature has no known activations.