© 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. 3205
    Prev
    Next
    INDEX
    Explanations

    возможно, нужно, но

    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
    ween
    -0.08
    ãģıãĤĮãģŁ
    -0.08
    зÑĢе
    -0.08
    ars
    -0.08
    говоÑĢ
    -0.07
    ä¼´ä½ł
    -0.07
    çļĦ
    -0.07
    zeÅĦ
    -0.07
    ãĤīãģ®
    -0.07
    arters
    -0.07
    POSITIVE LOGITS
    ed
    0.09
    иÑģк
    0.07
     pula
    0.07
     ÑģамомÑĥ
    0.07
    uÄį
    0.07
    Äĩe
    0.07
    Äĩ
    0.07
    ités
    0.07
     Åijket
    0.07
    es
    0.07
    Activations Density 0.016%

    No Known Activations