© 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. 44009
    Prev
    Next
    INDEX
    Explanations

    example : documentation

    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
    arih
    -0.08
     exclusivo
    -0.08
    .FC
    -0.07
    çĭ¬å®¶
    -0.07
    çį¨å®¶
    -0.07
    CMP
    -0.07
     eksklus
    -0.07
    ุà¹īม
    -0.07
     %[
    -0.07
    QueryBuilder
    -0.07
    POSITIVE LOGITS
    سÙĬ
    0.08
    ients
    0.07
    çĽ¸ä¿¡ä½ł
    0.07
    æĥĭ
    0.06
    arra
    0.06
    _multi
    0.06
    çķª
    0.06
    ujo
    0.06
    ä¾ĭ
    0.06
    ites
    0.06
    Activations Density 0.004%

    No Known Activations