© 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. 46307
    Prev
    Next
    INDEX
    Explanations

    word endings and inflections

    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
    otto
    -0.07
    ers
    -0.07
     exp
    -0.07
    uas
    -0.06
    çĻ»åħ¥
    -0.06
    ama
    -0.06
    iband
    -0.06
    ÙĬÙĪب
    -0.06
     unm
    -0.05
    ette
    -0.05
    POSITIVE LOGITS
    usen
    0.09
    é»ĦçīĽ
    0.08
    पà¥į
    0.08
    õt
    0.08
    ä¿Ŀ驾
    0.07
    ichtlich
    0.07
    _STANDARD
    0.07
    éĩįãģĦ
    0.07
    è¯ºåŁº
    0.07
    è¿Ļæĺ¯ä»ĸ
    0.07
    Activations Density 0.014%

    No Known Activations