© 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. 25-TRANSCODER-HP
    7. 109516
    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
    Negative Logits
     Vol
    -0.32
    fore
    -0.30
    AG
    -0.30
    [
    -0.30
    RE
    -0.30
     vol
    -0.29
     AG
    -0.28
    Vol
    -0.27
     RET
    -0.27
    VE
    -0.27
    POSITIVE LOGITS
    âĸ¸
    0.34
    åįĹæµ·
    0.28
    ä¹Ŀåįģ
    0.27
     davon
    0.26
    åij³
    0.25
    avad
    0.25
     distancing
    0.25
    alette
    0.25
     UID
    0.25
    ãģ©ãģĵãĤį
    0.25
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.