© 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. 2236
    Prev
    Next
    INDEX
    Explanations

    but, however

    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
    æľīåħ³æ³ķå¾ĭ
    -0.08
    å°Ķå¾·
    -0.08
     dealing
    -0.08
    мп
    -0.08
     dealt
    -0.07
    رس
    -0.07
    ä¸įä½Ĩ
    -0.07
    eload
    -0.07
    è¿ĺ以为
    -0.07
    ajn
    -0.07
    POSITIVE LOGITS
    ä¸įè¦ģ太
    0.08
    æ¸ł
    0.07
    ä¿ĿæĮģ
    0.07
    èij£
    0.06
    æĥľ
    0.06
    æĬ¬
    0.06
    ä¿ĿæĮģåľ¨
    0.06
    bill
    0.06
    ç½
    0.06
    ç´§
    0.06
    Activations Density 0.034%

    No Known Activations