© 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. 23-TRANSCODER-HP
    7. 25215
    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_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ään
    -0.29
    wash
    -0.26
    åħ¶æ¬¡
    -0.26
     grate
    -0.25
    ãģ¨åIJĮãģĺ
    -0.25
    NDAR
    -0.25
     ÑĤаким
    -0.25
    lö
    -0.25
    zie
    -0.23
    venient
    -0.23
    POSITIVE LOGITS
     whereas
    0.68
     Whereas
    0.66
    èĢĮ
    0.64
    èĢĮ对äºİ
    0.56
    èĢĮåľ¨
    0.54
    èĢĮæĪIJ
    0.50
    èĢĮåĩº
    0.49
    èĢĮæĿ¥
    0.48
     while
    0.45
     whilst
    0.45
    Activations Density 0.002%

    No Known Activations