© 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. 43384
    Prev
    Next
    INDEX
    Explanations

    map symbols

    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
    æŀ¶ä¸Ĭ
    -0.07
    rechnung
    -0.07
    zes
    -0.07
    cius
    -0.07
    ç»Ŀ
    -0.06
     Ganz
    -0.06
    ymo
    -0.06
    æıIJé«ĺ
    -0.06
    ä¼
    -0.06
    occo
    -0.06
    POSITIVE LOGITS
    æľįä»İ
    0.08
     inherits
    0.08
    们çļĦ
    0.08
    们
    0.08
    ansi
    0.08
    IDAS
    0.07
     xá»ī
    0.07
    æĪIJæŃ£
    0.07
    éĩij森
    0.07
    iosa
    0.07
    Activations Density 0.014%

    No Known Activations