© 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. 106927
    Prev
    Next
    INDEX
    Explanations

    Cities

    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
    Not in Any Lists

    No Comments

    Negative Logits
    agraph
    -0.28
    ìĬµ
    -0.27
    sprites
    -0.25
    uchs
    -0.25
     spray
    -0.24
     Wahl
    -0.23
    ror
    -0.23
    çļĦä¸įåIJĮ
    -0.23
    .RegisterType
    -0.23
    èĢĮåıĪ
    -0.23
    POSITIVE LOGITS
     ++↵
    0.29
    å·²äºİ
    0.27
    anse
    0.27
     Ves
    0.26
    è¿ĩæĿ¥
    0.25
    è·¨è¶Ĭ
    0.25
     hoped
    0.24
    nett
    0.24
    oga
    0.24
    åıįè¿ĩæĿ¥
    0.24
    Activations Density 13.479%

    No Known Activations