© 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. 128997
    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
    emie
    -0.28
    raig
    -0.28
    å©´
    -0.27
    rates
    -0.26
    mı
    -0.26
    -rating
    -0.25
     VIN
    -0.25
    á¿ĸ
    -0.25
     ecl
    -0.25
    êm
    -0.25
    POSITIVE LOGITS
    ok
    0.28
    éĻĦ
    0.26
    èĩªä»İ
    0.26
     Kendall
    0.25
     sure
    0.25
    åĽ½å®¶æłĩåĩĨ
    0.24
     familiar
    0.24
     pass
    0.23
    nd
    0.23
     ways
    0.23
    Activations Density 22.117%

    No Known Activations

    This feature has no known activations.