© 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. 20-TRANSCODER-HP
    7. 108768
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    brew
    -0.27
    inos
    -0.26
    bras
    -0.25
    thy
    -0.25
     Valve
    -0.24
    erval
    -0.24
    aval
    -0.24
    acre
    -0.24
     authorize
    -0.23
    æķ°æį®æĺ¾ç¤º
    -0.23
    POSITIVE LOGITS
    çĥĽ
    0.26
    æĺİæĹ¥
    0.26
    åıįè¿ĩæĿ¥
    0.25
    -days
    0.24
     tail
    0.24
    åĪ¶
    0.23
    rchive
    0.23
    orraine
    0.23
    åĩĿ
    0.23
    StackTrace
    0.23
    Activations Density 13.126%

    No Known Activations

    This feature has no known activations.