© 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. 13045
    Prev
    Next
    INDEX
    Explanations

    defined as, referred to as, conversion of

    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
    è¿ĻæŶçļĦ
    -0.08
    ÑģовеÑģÑĤ
    -0.08
    hoven
    -0.08
    Ñģнабжение
    -0.08
     اÙĦجارÙĬ
    -0.08
    ç½®ä¹ĭ
    -0.08
    Ñģпали
    -0.08
    евна
    -0.07
    iest
    -0.07
    åıĪä¸įèĥ½
    -0.07
    POSITIVE LOGITS
    (lr
    0.07
     pint
    0.06
    [table
    0.06
    (SP
    0.06
    éĿĵ丽
    0.06
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.06
    rim
    0.06
    çİ¥
    0.06
     LoggerFactory
    0.06
    (LED
    0.06
    Activations Density 0.122%

    No Known Activations