© 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. 2205
    Prev
    Next
    INDEX
    Explanations

    dates or currencies

    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
    èį¡èį¡
    -0.08
    зоÑĢ
    -0.07
    odian
    -0.07
    мелÑĮ
    -0.07
    atorio
    -0.07
    èĩªå¼ºä¸įæģ¯
    -0.07
    зÑĥ
    -0.07
    è§Ĵ度æĿ¥è¯´
    -0.07
    asename
    -0.07
    лка
    -0.07
    POSITIVE LOGITS
    çķ¥æľī
    0.07
    ç¼¥
    0.07
    uff
    0.07
    osaur
    0.07
    å»
    0.07
    __/
    0.06
    ç»ĵäºĨ
    0.06
    ade
    0.06
    å°ıå§IJ
    0.06
    ç¨įæľī
    0.06
    Activations Density 0.004%

    No Known Activations