© 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. 64560
    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
    Not in Any Lists

    No Comments

    Negative Logits
     exce
    -0.28
     smugg
    -0.27
     bidi
    -0.27
    лÑĮн
    -0.25
    cel
    -0.25
    åij¨ä¸ī
    -0.25
    pk
    -0.25
    lld
    -0.25
     spill
    -0.24
    weekly
    -0.24
    POSITIVE LOGITS
    èŀºä¸Ŀ
    0.28
    ä¸įåĪĨ
    0.27
     ì°
    0.25
    FFFFFF
    0.25
    Classification
    0.24
    legate
    0.24
    roma
    0.24
    å½ĵä½ľ
    0.24
    SIM
    0.24
    æĺ¯ä¸Ģéĥ¨
    0.24
    Activations Density 39.820%

    No Known Activations

    This feature has no known activations.