© 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. 31920
    Prev
    Next
    INDEX
    Explanations

    derivations and differentials

    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
    à§įড
    -0.07
    ously
    -0.07
    ı
    -0.07
    eh
    -0.07
    æĢ§åľ°
    -0.06
    ILLE
    -0.06
    Ù°
    -0.06
    onym
    -0.06
    lah
    -0.06
    à¹Ī
    -0.06
    POSITIVE LOGITS
    ات
    0.09
    sstr
    0.09
    ç»´å¥ĩ
    0.09
    eldes
    0.09
    sWith
    0.08
    kada
    0.08
    Ø©
    0.08
    gether
    0.08
    ought
    0.08
     quals
    0.07
    Activations Density 0.002%

    No Known Activations