© 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. 45402
    Prev
    Next
    INDEX
    Explanations

    numerical string 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
    رÙĬس
    -0.08
    arris
    -0.07
    éªģ
    -0.07
    æª
    -0.07
    جÙĬÙĨ
    -0.07
    uby
    -0.07
    ä½ķå¿ħ
    -0.07
    sic
    -0.07
     tombe
    -0.06
    olat
    -0.06
    POSITIVE LOGITS
    ITI
    0.08
    -inline
    0.07
    让æĪijä»¬åľ¨
    0.06
    ulas
    0.06
     Lem
    0.06
    çľŁå¥½
    0.06
    ัà¸į
    0.06
     Cure
    0.06
     Horiz
    0.06
    çĽĺä¸Ń
    0.06
    Activations Density 0.250%

    No Known Activations