© 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. 162506
    Prev
    Next
    INDEX
    Explanations

    Informal writing style

    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
    åİ»
    -0.31
     INF
    -0.30
    ä¸Ģ个æĸ°çļĦ
    -0.29
    åĬłåħ¥
    -0.28
     gaan
    -0.28
     onto
    -0.27
    æĪ´ä¸Ĭ
    -0.27
    èµ°åħ¥
    -0.25
    转移åĪ°
    -0.25
     into
    -0.25
    POSITIVE LOGITS
    currently
    0.32
     currently
    0.32
    çİ°åľ¨
    0.30
     now
    0.30
    	now
    0.29
     anymore
    0.28
    åĨĻçĿĢ
    0.28
    åĭĻ
    0.28
    缮åīį
    0.27
    ä»Ĭãģ¯
    0.27
    Activations Density 0.006%

    No Known Activations