© 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. 43290
    Prev
    Next
    INDEX
    Explanations

    article list

    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
    对å¾ħ
    -0.08
    çĤ
    -0.07
    eking
    -0.07
    ahal
    -0.07
    ä¸įçĽ¸ä¿¡
    -0.07
    äºĨèĩªå·±çļĦ
    -0.06
     overt
    -0.06
    ä¸įäºĨ解
    -0.06
    orer
    -0.06
    alent
    -0.06
    POSITIVE LOGITS
    ØŃÙĬØ©
    0.08
     chÃŃ
    0.07
    å·¥ä½ľä¸ŃçļĦ
    0.07
    祺
    0.07
    åĮ¡
    0.07
    withdraw
    0.07
    taa
    0.07
     vÃŃde
    0.07
    æīĵèµ¢
    0.07
    áĥ£áĥł
    0.07
    Activations Density 0.007%

    No Known Activations