© 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. 162287
    Prev
    Next
    INDEX
    Explanations

    actually

    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
    ç¡®å®ŀ
    -0.33
     indeed
    -0.31
    Indeed
    -0.28
    =https
    -0.27
    æ¯ķç«Łæĺ¯
    -0.26
    urement
    -0.26
     Indeed
    -0.26
    確ãģĭãģ«
    -0.26
    ç¡®å®ŀæĺ¯
    -0.25
    uyến
    -0.25
    POSITIVE LOGITS
     never
    0.31
     differ
    0.29
     rather
    0.29
    并ä¸įä¼ļ
    0.28
    å¹¶æľª
    0.28
     an
    0.28
    并没æľī
    0.27
    _algorithm
    0.26
     even
    0.26
    并ä¸į
    0.25
    Activations Density 0.014%

    No Known Activations