© 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. 163147
    Prev
    Next
    INDEX
    Explanations

    Data structures/computing concepts

    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
    å¦Ĥæŀľçݩ家
    -0.26
    å·¥åķĨ
    -0.25
    yst
    -0.25
     ones
    -0.25
    nde
    -0.25
    éĤª
    -0.24
     numer
    -0.24
    ynn
    -0.24
    _cast
    -0.24
    飶
    -0.24
    POSITIVE LOGITS
    fits
    0.31
     arranged
    0.30
    arning
    0.29
     labeled
    0.29
    uku
    0.28
    åIJĦèĩªçļĦ
    0.28
    åħ¬æĬ¥
    0.27
     interconnected
    0.26
     Matchers
    0.26
     treated
    0.26
    Activations Density 0.054%

    No Known Activations