© 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. 23577
    Prev
    Next
    INDEX
    Explanations

    without

    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
     lắm
    -0.08
    CANCEL
    -0.07
    TickCount
    -0.07
    estal
    -0.07
    ä½Ĩåı¯ä»¥
    -0.07
    æĥħåĨµæĿ¥çľĭ
    -0.07
    ä¹Łä¸įåı¯èĥ½
    -0.07
    ippe
    -0.07
    mad
    -0.07
     restless
    -0.07
    POSITIVE LOGITS
     without
    0.22
    without
    0.19
     ohne
    0.18
     Without
    0.18
     tanpa
    0.16
     بدÙĪÙĨ
    0.16
    Without
    0.16
     без
    0.16
     senza
    0.16
     WITHOUT
    0.15
    Activations Density 0.318%

    No Known Activations