© 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. 163452
    Prev
    Next
    INDEX
    Explanations

    bipolar disorder

    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
    ä¼łç»ŁçļĦ
    -0.32
    ieux
    -0.28
    æıIJåĩºçļĦ
    -0.28
    度
    -0.26
    -mort
    -0.25
    羡æħķ
    -0.24
    antic
    -0.24
    ä¼łç»Ł
    -0.24
    污æŁĵ
    -0.24
     Tah
    -0.24
    POSITIVE LOGITS
     reap
    0.29
    大åİħ
    0.26
    çĶŁæ´»ä¹łæĥ¯
    0.25
     recurrent
    0.25
    rices
    0.24
     hinge
    0.24
    aterangepicker
    0.24
    åĪ°æĿ¥
    0.24
     jitter
    0.24
    elles
    0.24
    Activations Density 0.001%

    No Known Activations