© 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. 29043
    Prev
    Next
    INDEX
    Explanations

    search by name or fields

    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
    èĢĹ
    -0.07
    é§Ĵ
    -0.07
    ä¸įåıij
    -0.07
    羽翼
    -0.07
    _HC
    -0.07
    IMS
    -0.07
    IPA
    -0.06
     gr
    -0.06
    yles
    -0.06
    åıĸä¸ĭ
    -0.06
    POSITIVE LOGITS
     criteria
    0.09
     combination
    0.09
     criterion
    0.08
     combinations
    0.08
     Criteria
    0.07
    æĿ¡ä»¶çļĦ
    0.07
     Combination
    0.07
    atch
    0.07
    aname
    0.07
     criter
    0.07
    Activations Density 0.001%

    No Known Activations