© 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. 13038
    Prev
    Next
    INDEX
    Explanations

    software, services, tools, management

    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
    åIJĦéĥ¨
    -0.07
    æĺ¥
    -0.06
    eto
    -0.06
    æģŃ
    -0.06
    è¿İ
    -0.06
    çĥŁ
    -0.06
    æĴ¬
    -0.06
     undes
    -0.06
    avings
    -0.06
     Descriptor
    -0.06
    POSITIVE LOGITS
    主æµģ
    0.11
     platforms
    0.10
    åĵªå®¶å¥½
    0.09
    /platform
    0.09
    主æµģçļĦ
    0.09
    åĵªå®¶
    0.09
    约èĢĮåIJĮ
    0.09
    ä¸ī家
    0.08
    èĢģçīĮ
    0.08
    åĵªä¸ªå¥½
    0.08
    Activations Density 0.463%

    No Known Activations