© 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. 106884
    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
     euler
    -0.26
     presente
    -0.24
    ADER
    -0.24
    æľīèĩªå·±çļĦ
    -0.23
    ç¥ĸ
    -0.23
     اÙĦخاÙħ
    -0.23
     reap
    -0.23
    (SIG
    -0.23
    èĪĤ
    -0.23
    å¹´çĶ±
    -0.23
    POSITIVE LOGITS
    atri
    0.28
    -license
    0.28
    basis
    0.27
    izin
    0.27
    ä¸ĭåįĬ
    0.26
    trip
    0.25
     Hod
    0.25
    hog
    0.24
    åĽłä¸ºä»ĸ们
    0.24
    ãĤĴéĢļãģĹãģ¦
    0.24
    Activations Density 7.101%

    No Known Activations

    This feature has no known activations.