© 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. 163206
    Prev
    Next
    INDEX
    Explanations

    Digits

    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
    itt
    -0.30
     call
    -0.25
    eres
    -0.25
     بÙĥ
    -0.25
    ill
    -0.25
     effective
    -0.25
     ahead
    -0.24
     tam
    -0.24
    ulta
    -0.24
    å½ĵæĹ¥
    -0.24
    POSITIVE LOGITS
    åĴĮ个人
    0.34
    æĬ¥éģĵ
    0.29
    æľĢåıĹ欢è¿İ
    0.27
     unbearable
    0.26
    çļĦæľĢåIJİä¸Ģ
    0.26
    -anchor
    0.25
    çļĦéĴ±
    0.25
    popular
    0.23
    ãĤĦ
    0.23
    eming
    0.23
    Activations Density 0.018%

    No Known Activations