© 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. 15257
    Prev
    Next
    INDEX
    Explanations

    takes on values

    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
    кÑĢÑĭ
    -0.07
     induk
    -0.07
    ippo
    -0.07
    å¦ŀ
    -0.07
    åĢ¾åĬĽ
    -0.06
    WARE
    -0.06
    æĪļ
    -0.06
     Marin
    -0.06
    à¹ĥหà¸įà¹Ī
    -0.06
     Ø´Ú©ÙĨ
    -0.06
    POSITIVE LOGITS
     values
    0.09
    åĢ¼
    0.08
    ivery
    0.08
     on
    0.08
    svp
    0.08
     tại
    0.08
     à¸ĵ
    0.08
    izzo
    0.08
    NECT
    0.08
     at
    0.08
    Activations Density 0.010%

    No Known Activations