© 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. 32022
    Prev
    Next
    INDEX
    Explanations

    unique solutions and 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
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    -0.09
    ciano
    -0.08
    åľ¨å»º
    -0.08
    à¹Ģà¸ģร
    -0.08
    fra
    -0.08
    mgr
    -0.08
    ä»»æĢ¨
    -0.08
    ä¸ĥ大
    -0.07
    egger
    -0.07
    çĻ½å±±
    -0.07
    POSITIVE LOGITS
     solutions
    0.07
    符åIJĪæĿ¡ä»¶
    0.07
    _mappings
    0.07
    符åIJĪæĿ¡ä»¶çļĦ
    0.07
    aye
    0.06
    éºŁ
    0.06
     distinct
    0.06
     viable
    0.06
    istence
    0.06
     Solutions
    0.06
    Activations Density 0.004%

    No Known Activations