© 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. 24185
    Prev
    Next
    INDEX
    Explanations

    date or approximately

    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
    ä¸į严
    -0.08
    产åĵģç»ĵæŀĦ
    -0.07
    wap
    -0.07
    à¦ł
    -0.07
    éľ²å¤´
    -0.07
    æ£ļæĪ·åĮº
    -0.07
    ä¸įå¤ļçļĦ
    -0.07
    æĹĹé¼ĵ
    -0.07
    esa
    -0.07
    eto
    -0.07
    POSITIVE LOGITS
    lops
    0.08
     numer
    0.07
    оÑģÑĤа
    0.07
    ä»¿çľŁ
    0.06
     ($.
    0.06
     ÅĻe
    0.06
    áŀ
    0.06
    .jupiter
    0.06
     Numer
    0.06
     stuff
    0.06
    Activations Density 0.006%

    No Known Activations