© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4551
    Prev
    Next
    INDEX
    Explanations

    states and statuses

    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
    ...).
    -0.07
    ç¾½
    -0.07
    究竣æĺ¯
    -0.07
    ?".
    -0.07
    âĢ¦).
    -0.07
    ...'
    -0.07
    emt
    -0.07
    èĢĮä¸įæĺ¯
    -0.06
    æī©å±ķèµĦæĸĻ
    -0.06
    kev
    -0.06
    POSITIVE LOGITS
     зо
    0.08
    已形æĪIJ
    0.08
    igno
    0.07
    主è¦ģä½ĵçİ°åľ¨
    0.07
    æ±Ģ
    0.07
     torm
    0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    0.07
     ãģŁãģłãģĹ
    0.07
    ä¸Ĭ大
    0.07
    æľī天
    0.06
    Activations Density 0.008%

    No Known Activations