© 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. 163312
    Prev
    Next
    INDEX
    Explanations

    mathematical/scientific problems

    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
     irrelevant
    -0.28
    缩å°ı
    -0.27
    å°ij
    -0.26
    öt
    -0.26
    ç»Ń
    -0.24
    icide
    -0.24
    ç»ıæŁ¥
    -0.23
    äºĨæĪijçļĦ
    -0.23
     mid
    -0.23
     thanks
    -0.23
    POSITIVE LOGITS
     General
    0.34
     GENERAL
    0.31
     generalized
    0.30
    GENERAL
    0.29
    General
    0.29
     general
    0.29
    general
    0.28
    æ³Ľ
    0.28
     generalize
    0.28
     fran
    0.28
    Activations Density 0.009%

    No Known Activations