© 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. 61060
    Prev
    Next
    INDEX
    Explanations

    spider, junior, exchange, marvel, collection

    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
    ä¸Ģå¾ĭ
    -0.08
    िन
    -0.07
    åĩºèĩª
    -0.07
    ãģĵãģ¡ãĤīãĤĤ
    -0.07
    '%(
    -0.07
    egah
    -0.07
    हन
    -0.07
     antaranya
    -0.07
    alach
    -0.07
    -css
    -0.07
    POSITIVE LOGITS
    å°±æĺ¯è¿Ļä¹Ī
    0.08
    å°±æĺ¯è¿Ļæł·
    0.07
     btw
    0.06
    èĢĮéĿŀ
    0.06
    å°±è¿Ļä¹Ī
    0.06
     Prós
    0.06
    èĢĮå°±
    0.06
    yce
    0.06
    ennon
    0.06
    ÅĤady
    0.05
    Activations Density 0.165%

    No Known Activations