© 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. 163521
    Prev
    Next
    INDEX
    Explanations

    Technical and verb language

    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
    edly
    -0.30
    ÃĹ↵↵
    -0.26
    è¡Ĺéģĵ
    -0.25
    è¡Ĺ
    -0.25
    æľĢä½³
    -0.24
     surf
    -0.24
     tác
    -0.24
    度
    -0.24
    è¯ij
    -0.23
    é«ĺæĺĤ
    -0.23
    POSITIVE LOGITS
    entic
    0.28
    otec
    0.25
     occurred
    0.25
    éĴŀ
    0.25
    tings
    0.24
    itus
    0.24
    ucken
    0.24
    ayar
    0.24
     occur
    0.24
    太快
    0.24
    Activations Density 0.079%

    No Known Activations