© 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. 62731
    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
    tica
    -0.24
     _:
    -0.24
    agus
    -0.24
    èµ°åĩºåİ»
    -0.23
     gradient
    -0.23
    CCA
    -0.23
     showDialog
    -0.23
     neighb
    -0.23
    apat
    -0.23
    ähr
    -0.23
    POSITIVE LOGITS
    éĿĵ
    0.31
    ä¸ļä½Ļ
    0.30
    _br
    0.26
    BALL
    0.26
     rein
    0.26
     professionally
    0.25
    ç±»
    0.25
    xs
    0.25
    _ax
    0.25
     dam
    0.24
    Activations Density 9.968%

    No Known Activations

    This feature has no known activations.