© 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. 32140
    Prev
    Next
    INDEX
    Explanations

    conclusion or wrap up

    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
    ä¿¡æģ¯ä¸¾æĬ¥
    -0.09
     Kunde
    -0.09
    è½¬è½½çĽ®çļĦåľ¨äºİä¼łéĢĴæĽ´å¤ļä¿¡æģ¯
    -0.09
    ụng
    -0.09
    .jquery
    -0.08
    onne
    -0.08
    ieber
    -0.08
    alach
    -0.08
     Merke
    -0.08
    æ·±åıĹ广大
    -0.08
    POSITIVE LOGITS
    à¸ĺิ
    0.07
    éĩįçĶ³
    0.06
    åįĩåįİ
    0.06
    对æķ´ä¸ª
    0.06
     reaff
    0.06
     briefly
    0.06
    æĪ´ä¸Ĭ
    0.06
     reinforcing
    0.06
    åĺī
    0.06
    ç®ĢçŁŃ
    0.06
    Activations Density 0.008%

    No Known Activations