© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31289
    Prev
    Next
    INDEX
    Explanations

    citations with r or R

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igheid
    -0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    -0.08
    æľ¬æĸĩ为åįļ主
    -0.07
     STDERR
    -0.07
    -await
    -0.07
     Postado
    -0.07
    ắp
    -0.07
    éĺ¿æĭī伯
    -0.07
    xon
    -0.07
    tras
    -0.07
    POSITIVE LOGITS
     bại
    0.07
    ÌĢ
    0.06
    æĶ¶å½ķ
    0.06
    ruk
    0.06
    æ¸
    0.06
    éĥ½æĺ¯åı¯ä»¥
    0.06
    cba
    0.06
    .types
    0.06
    åħij
    0.06
     end
    0.06
    Activations Density 0.470%

    No Known Activations