© 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. 58035
    Prev
    Next
    INDEX
    Explanations

    measurement or quantity

    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
    å°ıå·§
    -0.07
    ä¸Ńå¿ĥ
    -0.06
    emen
    -0.06
    æľīä½Ļ
    -0.06
    osit
    -0.06
    æĮ¡
    -0.06
    ä½łæĿ¥
    -0.06
     Neur
    -0.06
    åħĥé¦ĸ
    -0.06
    coni
    -0.06
    POSITIVE LOGITS
     thereof
    0.16
    ä¸İä¹ĭ
    0.12
     therein
    0.12
    对åħ¶è¿Ľè¡Į
    0.10
    æĬĬå®ĥ们
    0.10
    å°Ĩå®ĥ们
    0.10
    对å®ĥ
    0.09
     ervan
    0.09
     associated
    0.09
    对åħ¶
    0.09
    Activations Density 0.315%

    No Known Activations