© 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. 58612
    Prev
    Next
    INDEX
    Explanations

    private keys

    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
     vaga
    -0.08
     пÑĥÑģÑĤ
    -0.07
    á»Ļp
    -0.07
    yth
    -0.06
    æĿ¯æ°´
    -0.06
     вакан
    -0.06
    QUEUE
    -0.06
     filler
    -0.06
    جاج
    -0.06
    nje
    -0.06
    POSITIVE LOGITS
    ç§ĺå¯Ĩ
    0.09
    çĶ¨äºİ
    0.09
    éĴ¥åĮĻ
    0.08
    Pair
    0.08
     usable
    0.08
    ä¿Ŀå¯Ĩ
    0.08
     secret
    0.08
    çļĦç§ĺå¯Ĩ
    0.08
    pair
    0.08
    è¿ĻæĬĬ
    0.08
    Activations Density 0.050%

    No Known Activations