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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163528
    Prev
    Next
    INDEX
    Explanations

    attracting and interesting

    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
    ignment
    -0.27
    roman
    -0.27
    angkan
    -0.26
    hof
    -0.26
    ãģ¾ãĤĬ
    -0.26
    igned
    -0.26
    utable
    -0.25
    åģĥ
    -0.25
    Ñīи
    -0.25
    .Ribbon
    -0.25
    POSITIVE LOGITS
    人们çļĦ
    0.32
    客åķĨ
    0.32
    æµ·åĨħå¤ĸ
    0.32
    åŁİ乡å±ħæ°ij
    0.32
    ä¸ĸçķĮåIJĦåĽ½
    0.31
     Matth
    0.30
    åĽ½äºº
    0.30
    人群
    0.28
     tel
    0.28
     travelers
    0.28
    Activations Density 0.002%

    No Known Activations