© 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. 3172
    Prev
    Next
    INDEX
    Explanations

    names in parentheses

    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
    æĹłåıį顾
    -0.07
    exo
    -0.07
    æĿİè½»
    -0.07
    å¦Ĥçİī
    -0.06
    æĬĬå·¥ä½ľ
    -0.06
    ém
    -0.06
    æĬĬéĤ£
    -0.06
    eros
    -0.06
    emente
    -0.06
    ä¸Ĭä¹Ł
    -0.06
    POSITIVE LOGITS
    æ°ı
    0.09
    ä¼¯æł¼
    0.08
    äºĮä¸ĸ
    0.08
    åħ¹
    0.08
    ·
    0.08
    ç»´å¥ĩ
    0.08
    夫人
    0.08
    Ỽt
    0.08
    å°ıåŃIJ
    0.08
    çIJª
    0.07
    Activations Density 0.004%

    No Known Activations