© 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. 24-TRANSCODER-HP
    7. 150185
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loor
    -0.27
    æ¼Ĩ
    -0.26
    antz
    -0.25
     mÃŃn
    -0.24
    ilm
    -0.23
    ollywood
    -0.23
    æĥħ
    -0.23
     assignable
    -0.23
    live
    -0.23
    çļĦåĬ¨ä½ľ
    -0.23
    POSITIVE LOGITS
    ä¸Ģ天
    0.54
    ä¸ĢæĹ¥
    0.53
     daily
    0.50
    æĹ©æĻ¨
    0.50
    /day
    0.47
     morning
    0.47
    æ¯ı天
    0.46
    åij¨ä¸Ģ
    0.46
    ä¸ŃåįĪ
    0.46
    ä¸ĬåįĪ
    0.45
    Activations Density 1.098%

    No Known Activations