© 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. 11574
    Prev
    Next
    INDEX
    Explanations

    electron partner

    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
     напо
    -0.07
     lim
    -0.07
    æĹłæķ°æ¬¡
    -0.07
    åłĢ
    -0.06
    éĢł
    -0.06
    ä¸Ģ次次
    -0.06
     haul
    -0.06
    ä¸īèĢħ
    -0.06
    quo
    -0.06
    æĭ¦
    -0.06
    POSITIVE LOGITS
    æĸĩåºĵ
    0.09
    /template
    0.07
    غÙĦ
    0.07
    çĭ¬è¡Į
    0.07
    åĬ¨æīĭ
    0.07
    _partner
    0.07
    ĥĿ
    0.07
    缮æłĩä»»åĬ¡
    0.07
    riad
    0.07
    ivid
    0.07
    Activations Density 0.001%

    No Known Activations