© 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. 48376
    Prev
    Next
    INDEX
    Explanations

    scientific and technical descriptions

    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
    ¦
    -0.07
    ä¸Ĭè¿°ä½ľåĵģ
    -0.07
    ingles
    -0.06
    ecz
    -0.06
     perv
    -0.06
    ello
    -0.06
    æĽ´éľĢè¦ģ
    -0.06
    çļĦåij¢
    -0.06
    人æĿ¥è¯´
    -0.06
    é¦Ļå¥Ī
    -0.06
    POSITIVE LOGITS
    æĽĻ
    0.08
    å±ķå¼Ģåħ¨æĸĩ
    0.08
    åľ¨ä¸Ģ
    0.07
    å½ĵä¸Ģ个
    0.07
    lez
    0.07
    /effects
    0.07
    çĹĬ
    0.07
    çı
    0.07
    agma
    0.07
    veux
    0.07
    Activations Density 0.022%

    No Known Activations