© 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. 13158
    Prev
    Next
    INDEX
    Explanations

    group or entity names

    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
    æv
    -0.07
    igd
    -0.07
    å³¥
    -0.07
    ught
    -0.07
    olls
    -0.07
    igel
    -0.07
    ->$
    -0.07
    sev
    -0.07
    åįıåĴĮ
    -0.06
    çĽ¸ä¿¡æĪij
    -0.06
    POSITIVE LOGITS
    à¦Łà¦¿
    0.11
    à¦Łà¦¿à¦°
    0.10
    æľ¬èº«çļĦ
    0.09
     itself
    0.09
    aster
    0.09
    æľ¬èº«
    0.08
    's
    0.08
    wide
    0.08
    åIJį称
    0.08
    ektor
    0.07
    Activations Density 0.752%

    No Known Activations