© 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. 13831
    Prev
    Next
    INDEX
    Explanations

    lakh crore

    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
    stat
    -0.07
    orre
    -0.06
    itary
    -0.06
    åľ¨èº«
    -0.06
    lee
    -0.06
    ¨
    -0.06
    isin
    -0.06
     Part
    -0.06
    ä¸Ģæ»´
    -0.06
     Yin
    -0.05
    POSITIVE LOGITS
    ikota
    0.09
    aths
    0.08
    hack
    0.08
    ë²ķìĿ¸
    0.08
    uille
    0.07
     اÙĦÙĩد
    0.07
    ikov
    0.07
    acters
    0.07
    TabIndex
    0.07
    à®Łà¯ģதà¯įதà¯ģ
    0.07
    Activations Density 0.203%

    No Known Activations