© 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. 25271
    Prev
    Next
    INDEX
    Explanations

    logging format specifiers

    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
    onyme
    -0.07
    STD
    -0.07
    ä¸Ģ缴ä¿ĿæĮģ
    -0.06
    omite
    -0.06
    retta
    -0.06
    ":""
    -0.06
    /umd
    -0.06
     Emas
    -0.06
    å®Į
    -0.06
    ä¸Ģ寸
    -0.06
    POSITIVE LOGITS
    atching
    0.07
    ULK
    0.07
    ISCO
    0.07
    èĭ¥å¹²éĹ®é¢ĺçļĦ
    0.07
    zens
    0.07
    丰ç¡ķ
    0.07
    ATCH
    0.06
    ÑĢÑıдÑĥ
    0.06
    寥
    0.06
    oner
    0.06
    Activations Density 0.141%

    No Known Activations