© 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. 130824
    Prev
    Next
    INDEX
    Explanations

    medicine 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
    Not in Any Lists

    No Comments

    Negative Logits
    éĢł
    -0.29
    æ¸ļ
    -0.28
     manners
    -0.28
    èİ·æĤī
    -0.27
    illian
    -0.26
    转åŀĭåıijå±ķ
    -0.26
    tau
    -0.26
     crow
    -0.24
    ç»Ħç»ĩå®ŀæĸ½
    -0.23
    å°ij
    -0.23
    POSITIVE LOGITS
    @param
    0.25
    jem
    0.24
    ogra
    0.24
    èĢĮçİ°åľ¨
    0.24
    hp
    0.24
    èıħ
    0.24
    éĥ½è¦ģ
    0.24
    >}↵
    0.24
     Seymour
    0.24
     sino
    0.24
    Activations Density 13.299%

    No Known Activations