© 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. 17951
    Prev
    Next
    INDEX
    Explanations

    searching for specific problems

    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
    achsen
    -0.07
    æŀģå¤§åľ°
    -0.07
    ÏĦε
    -0.07
     europé
    -0.07
     ayer
    -0.07
    _aliases
    -0.07
    ضر
    -0.07
    æł¼å°Ķ
    -0.06
    ÈĽele
    -0.06
    vue
    -0.06
    POSITIVE LOGITS
    åį°è±¡ä¸Ń
    0.07
    omid
    0.07
    å·®ä¸įå¤ļäºĨ
    0.07
    缸åħ³çļĦåĨħ容
    0.07
    çļĦ缸åħ³ä¿¡æģ¯
    0.07
    æľīåħ³äºİ
    0.07
    类似éĹ®é¢ĺ
    0.07
    å¼
    0.07
    åľ°åıijçİ°
    0.07
    arel
    0.07
    Activations Density 0.004%

    No Known Activations