© 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. 17076
    Prev
    Next
    INDEX
    Explanations

    Simon Glass or dates and times

    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
    æ¼
    -0.06
     ê°Ī
    -0.06
    马ä¸Ĭ
    -0.06
    æĺŃ
    -0.06
    Subsystem
    -0.06
    è¶
    -0.06
     ÑģмоÑĤÑĢÑı
    -0.06
    ĸ
    -0.06
    ãģ¾ãģ¾
    -0.06
    èĢĹ
    -0.06
    POSITIVE LOGITS
    exion
    0.08
    éĻĦ件
    0.08
    å¿ĥçĶ°
    0.08
    åįĩåĪĿ
    0.07
    影幽
    0.07
    esito
    0.07
    好å¿ĥæĥħ
    0.07
    ix
    0.07
    finity
    0.07
    _ios
    0.07
    Activations Density 0.001%

    No Known Activations