© 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. 62585
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical processes

    np_max-act · gemini-2.0-flash
    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
    rna
    -0.28
    vs
    -0.26
    ä¸İåIJ¦
    -0.26
    æľªæĪIJ
    -0.26
    aken
    -0.25
    cca
    -0.25
    m
    -0.25
    ess
    -0.24
    ç§ĭåĨ¬
    -0.24
    gm
    -0.24
    POSITIVE LOGITS
     scrim
    0.29
     Yankee
    0.25
    ovement
    0.25
    è¶Ĭ大
    0.24
    BuilderFactory
    0.24
    омеÑĢ
    0.24
    äºĨæĪijçļĦ
    0.24
     CHtml
    0.24
     Dak
    0.24
    (`<
    0.23
    Activations Density 20.545%

    No Known Activations