© 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. 10528
    Prev
    Next
    INDEX
    Explanations

    specific phrases and punctuation

    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
    ãĤ¤ãĥ³ãĥĪ
    -0.07
     primi
    -0.06
    纽
    -0.06
    æİĮæı¡å¥½
    -0.06
    .Does
    -0.06
    ä½Ĩæĺ¯ä»İ
    -0.06
    avn
    -0.06
    çĥ¨
    -0.06
    unner
    -0.06
    noch
    -0.06
    POSITIVE LOGITS
    é«ĺå±±
    0.08
    abcdefghijkl
    0.08
    åĵĴ
    0.07
    lists
    0.07
    çĶĺå¿ĥ
    0.07
    åľ°ä¹ħ
    0.07
     hustle
    0.07
    FixedSize
    0.07
    çĿ¿æĻº
    0.07
    æľīæĪij
    0.07
    Activations Density 0.010%

    No Known Activations