© 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. 62276
    Prev
    Next
    INDEX
    Explanations

    list structures and data organization

    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
    unsch
    -0.07
    panse
    -0.07
    eden
    -0.07
    æ¶īåıĬ
    -0.07
    ä¸įè´Łè´£
    -0.07
    ÑģÑı
    -0.07
    æīĢè°ĵ
    -0.07
    è¡·
    -0.07
     Blow
    -0.07
    æ¶īåıĬåĪ°
    -0.07
    POSITIVE LOGITS
     vice
    0.07
    ä¸ĢåŃĹ
    0.07
     equivalence
    0.07
     Il
    0.06
    ambu
    0.06
    å¯Ĩä¸įåı¯åĪĨ
    0.06
    æĴ®
    0.06
    rying
    0.06
    åħ«æľĪ
    0.06
    вал
    0.06
    Activations Density 0.110%

    No Known Activations