© 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. 129275
    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
    çĵ¶é¢Ī
    -0.30
    å¸IJ篷
    -0.29
    该
    -0.28
    éĩĮç¨ĭç¢ij
    -0.28
    該
    -0.27
     pret
    -0.26
    None
    -0.26
     Guil
    -0.25
    åħ³åı£
    -0.25
    è§Ħ模æľĢ大
    -0.25
    POSITIVE LOGITS
    otas
    0.28
    _SUITE
    0.28
    USAGE
    0.25
    acier
    0.25
    anta
    0.25
    è
    0.25
    uras
    0.24
     feared
    0.24
    _UPLOAD
    0.24
    æļ´
    0.24
    Activations Density 2.809%

    No Known Activations

    This feature has no known activations.