© 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. 13416
    Prev
    Next
    INDEX
    Explanations

    world

    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
    ellent
    -0.07
    eld
    -0.07
    åį³å°ĨåĪ°æĿ¥
    -0.07
    æľ¬æĬ¥è®¯
    -0.07
     ==>
    -0.07
     conting
    -0.06
    ä¸ĭåIJĮ
    -0.06
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.06
    #from
    -0.06
    _FD
    -0.06
    POSITIVE LOGITS
    ä¸Ģæĸ°çļĦ
    0.08
    æŃ£åĢ¼
    0.07
    æīĢæ¶īåıĬ
    0.07
    صة
    0.07
     Pocket
    0.07
    ç¿
    0.07
    èĬ±ä¸Ģ
    0.07
    inä
    0.07
    æ¦ĤåĨµ
    0.07
    à§ĭà¦Ł
    0.07
    Activations Density 0.160%

    No Known Activations