© 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. 38066
    Prev
    Next
    INDEX
    Explanations

    numbers and enumeration

    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
    å¾ĹæĦı
    -0.09
    ä½Ĩæĺ¯å½ĵ
    -0.08
    assel
    -0.08
    ä¸įéĢı
    -0.08
    è¿ĩ头
    -0.07
    æĬĬ人
    -0.07
    Ñģква
    -0.07
    ç»İ
    -0.07
    Sac
    -0.07
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.07
    POSITIVE LOGITS
    æľĪçĶŁ
    0.08
    _ATTR
    0.07
    اعت
    0.07
     punc
    0.06
    ä¹Įäºij
    0.06
    ruÄį
    0.06
    occhi
    0.06
     puta
    0.06
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.06
     KR
    0.06
    Activations Density 0.006%

    No Known Activations