© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46657
    Prev
    Next
    INDEX
    Explanations

    geometric series

    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
    åĻª
    -0.08
    nil
    -0.07
    éºĴ
    -0.07
    éľ
    -0.07
    iris
    -0.07
    _OVERRIDE
    -0.07
    éĽªä¸Ń
    -0.07
    indung
    -0.07
     Shades
    -0.07
    à¸Ľà¸¥à¸Ńà¸Ķ
    -0.07
    POSITIVE LOGITS
    大åIJį
    0.08
    æıIJè¦ģ
    0.07
    åºķçļĦ
    0.07
    itom
    0.07
    åıijæķ£
    0.07
    ummer
    0.07
    ogna
    0.07
    æĮĩæķ°
    0.07
    _threads
    0.07
    æ¶ĪåĮĸä¸įèī¯
    0.07
    Activations Density 0.009%

    No Known Activations