© 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. 15284
    Prev
    Next
    INDEX
    Explanations

    area of and

    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
    hamn
    -0.06
    æĭ¥
    -0.06
    usy
    -0.06
    éten
    -0.06
    றி
    -0.06
    äºĭ
    -0.06
    ange
    -0.06
    teri
    -0.06
    é»Ħæ²Ļ
    -0.06
    ¯
    -0.05
    POSITIVE LOGITS
    çī¹æ´¾
    0.08
    æĶ¶èĹıæľ¬ç«Ļ
    0.07
    ĤŃ
    0.07
    enna
    0.07
    beck
    0.07
    andon
    0.07
    кеÑĤ
    0.07
    оÑī
    0.07
    åıĮåĪĽ
    0.07
    豪
    0.07
    Activations Density 0.055%

    No Known Activations