© 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. 7834
    Prev
    Next
    INDEX
    Explanations

    method names and programming constructs

    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
    è´£ç¼ĸ
    -0.07
     ;-
    -0.07
    å²Ń
    -0.06
    Ur
    -0.06
    å¼Ł
    -0.06
    _algo
    -0.06
    ä¹ĭä¸į
    -0.06
    çĵ®
    -0.06
    FK
    -0.06
    žite
    -0.06
    POSITIVE LOGITS
    acker
    0.08
    æĿ¥æŶ
    0.08
    æ¿ĢåıijäºĨ
    0.07
    à¸Ĭิà¸ĩ
    0.06
    ç§įçļĦ
    0.06
    åħħ
    0.06
    ÙĪÙģرة
    0.06
    ãĤ»ãĤ¤
    0.06
    baka
    0.06
    -Disposition
    0.06
    Activations Density 0.080%

    No Known Activations