© 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. 162451
    Prev
    Next
    INDEX
    Explanations

    will

    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
    fits
    -0.33
    ä¸įæĺ¯ä¸Ģ个
    -0.29
    еÑģÑĤв
    -0.28
    并ä¸įå¤ļ
    -0.28
    éĩįéĩį
    -0.27
     promotion
    -0.26
    fit
    -0.26
     dominates
    -0.26
    Fit
    -0.26
    妨ç¢į
    -0.25
    POSITIVE LOGITS
     sometimes
    0.41
    æľīæŶ
    0.40
     occasionally
    0.38
    æľīæŶåĢĻ
    0.37
     Sometimes
    0.34
    ä¹ŁçŁ¥éģĵ
    0.33
    sometimes
    0.32
    åģ¶å°Ķ
    0.32
     occasional
    0.32
     Occasionally
    0.31
    Activations Density 0.001%

    No Known Activations