© 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. 63229
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    æĦıæĢĿ
    -0.28
    emarks
    -0.25
    edo
    -0.23
    bih
    -0.22
    abilidad
    -0.21
    à¹Ģà¸Ĺ
    -0.21
    اÙĩ
    -0.21
    AMES
    -0.20
    rito
    -0.20
    erging
    -0.20
    POSITIVE LOGITS
    ...",↵
    0.26
    ...'
    0.25
    ...',↵
    0.25
    æŁ¥çľĭåħ¨æĸĩ
    0.23
    aits
    0.23
    çľ¼è§Ĵ
    0.23
    isnan
    0.23
    ...";↵
    0.22
    ...↵↵↵↵
    0.22
    人å±ħ
    0.22
    Activations Density 13.196%

    No Known Activations