© 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. 13109
    Prev
    Next
    INDEX
    Explanations

    law and evidence

    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
    nyi
    -0.08
     unsustainable
    -0.07
     oversh
    -0.06
    _feedback
    -0.06
    使åij½
    -0.06
    åĻ
    -0.06
    æĹ¥å¤ľ
    -0.06
    _defined
    -0.06
    oldown
    -0.06
    Feedback
    -0.06
    POSITIVE LOGITS
    ä¼łåĶ¤
    0.10
    è¯ģ人
    0.10
    ä½ľè¯ģ
    0.10
    ç¬Ķå½ķ
    0.09
    è´¨è¯ģ
    0.09
     interrog
    0.08
     testimony
    0.08
    éĩĩä¿¡
    0.08
    åĩºåºŃ
    0.08
     показаниÑı
    0.08
    Activations Density 0.031%

    No Known Activations