© 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. 32453
    Prev
    Next
    INDEX
    Explanations

    below or above

    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
    就好
    -0.08
    ازÛĮ
    -0.08
    说ä¸įåĩºçļĦ
    -0.07
    orien
    -0.07
    ļľ
    -0.07
    åįĬæľĪ
    -0.07
    cter
    -0.07
    erialized
    -0.07
    icamente
    -0.07
    å°±å½ĵ
    -0.07
    POSITIVE LOGITS
     below
    0.13
    ä¸ĭéĿ¢
    0.12
    below
    0.11
     outlined
    0.10
     shown
    0.10
    ä¸ĬéĿ¢
    0.09
     above
    0.09
     ниже
    0.09
    à¸Ĥà¹īาà¸ĩ
    0.09
    shown
    0.09
    Activations Density 0.513%

    No Known Activations