© 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. 27-TRANSCODER-HP
    7. 58353
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distancia
    -0.30
    çļĦè·Ŀ离
    -0.28
    è·Ŀ离
    -0.28
     Distance
    -0.27
     distance
    -0.27
     gent
    -0.27
    uida
    -0.27
    è¡ĢèĦī
    -0.26
    ç¿Ĭ
    -0.26
    jähr
    -0.26
    POSITIVE LOGITS
    çªģåĩºéĹ®é¢ĺ
    0.33
     hitch
    0.29
    (exports
    0.28
    iere
    0.26
    avy
    0.26
    åĽ½éĺ²
    0.25
     defence
    0.25
    æİ¡
    0.24
     reached
    0.24
    èĬľ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.