© 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. 140576
    Prev
    Next
    INDEX
    Explanations

    Space and technology

    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
    avic
    -0.26
    -animate
    -0.26
    APPED
    -0.26
    oked
    -0.25
    arded
    -0.24
    apped
    -0.24
    æ¯Ľ
    -0.24
     '~
    -0.23
    illion
    -0.23
    éļıæľº
    -0.23
    POSITIVE LOGITS
    ustum
    0.26
    swift
    0.26
    åıªåī©ä¸ĭ
    0.25
     slides
    0.25
    slide
    0.25
     indifference
    0.24
    é«ĺéĢŁ
    0.24
    _infos
    0.24
    trusted
    0.23
    è°Īè°Ī
    0.23
    Activations Density 4.212%

    No Known Activations