© 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. 3511
    Prev
    Next
    INDEX
    Explanations

    including miscellaneous items

    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
     lạc
    -0.08
    ÙĦائ
    -0.08
    iom
    -0.08
    ä¹Ŀ天
    -0.07
    æľīåħ³æ³ķå¾ĭ
    -0.07
    onos
    -0.07
    -stage
    -0.07
    QueryBuilder
    -0.07
     ogn
    -0.07
    rach
    -0.07
    POSITIVE LOGITS
    éĿ¢å¹¿
    0.08
    çļĦè¿ĺæľī
    0.08
    ä¹ŁåĮħæĭ¬
    0.08
    æŀģäºĨ
    0.08
    ungen
    0.08
     those
    0.07
    éĤ£äºĽ
    0.07
     lẫn
    0.07
    /rem
    0.07
     possibilité
    0.07
    Activations Density 0.026%

    No Known Activations