© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2635
    Prev
    Next
    INDEX
    Explanations

    翻天

    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
    oose
    -0.08
    OrFail
    -0.07
    PrototypeOf
    -0.07
    覧
    -0.07
    обÑĢ
    -0.07
    éļ¾æ±Ĥ
    -0.07
    è¡Į驶çļĦ
    -0.07
    .Priority
    -0.07
    /docs
    -0.07
    licit
    -0.07
    POSITIVE LOGITS
    翻天
    0.07
    åªĽ
    0.07
    达产年
    0.07
    æĪIJæŃ£
    0.07
    acey
    0.07
    ATER
    0.06
    åħĭåħ°
    0.06
    ì²ĺ
    0.06
     topLeft
    0.06
    为çĶŁ
    0.06
    Activations Density 0.066%

    No Known Activations