© 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. 108754
    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
    orr
    -0.25
     bell
    -0.25
     wedge
    -0.24
    gn
    -0.24
    CAS
    -0.24
    ån
    -0.24
    æīĵåĬ¨
    -0.24
    zon
    -0.24
    nan
    -0.23
     tas
    -0.23
    POSITIVE LOGITS
    åı£å¤´
    0.28
    çĽĤ
    0.27
     rent
    0.27
    á»Ĭ
    0.26
    FunctionFlags
    0.24
    arith
    0.24
    หาร
    0.24
    idden
    0.24
    irection
    0.23
    arah
    0.23
    Activations Density 13.533%

    No Known Activations

    This feature has no known activations.