© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107962
    Prev
    Next
    INDEX
    Explanations

    Punctuation and common words

    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
    çķ¥å¾®
    -0.35
    çķ¥æľī
    -0.33
    å°ij许
    -0.32
    éĢĤ度
    -0.31
     moderation
    -0.29
    ç¨įå¾®
    -0.29
    åģ¶å°Ķ
    -0.28
    åĽºçĦ¶
    -0.28
     moderately
    -0.28
     SOME
    -0.28
    POSITIVE LOGITS
    ate
    0.30
     reg
    0.28
    ize
    0.28
    peat
    0.28
    躺çĿĢ
    0.27
    unnel
    0.26
    ates
    0.26
    end
    0.26
    年以æĿ¥
    0.25
     Rodrigo
    0.25
    Activations Density 50.211%

    No Known Activations