© 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. 90237
    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
    LOGGER
    -0.31
     malignant
    -0.28
     filt
    -0.28
    .LINE
    -0.27
    è´¢
    -0.25
    éħĨ
    -0.25
     Closet
    -0.25
     desk
    -0.25
     Screen
    -0.25
     Rules
    -0.24
    POSITIVE LOGITS
    åĢĴåľ¨
    0.29
    rich
    0.26
    inline
    0.26
    tid
    0.26
     readiness
    0.25
    иÑħ
    0.25
    zp
    0.24
    åİ»æİī
    0.24
    (comb
    0.24
     %[
    0.24
    Activations Density 33.059%

    No Known Activations

    This feature has no known activations.