© 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. 41395
    Prev
    Next
    INDEX
    Explanations

    mathematical indices and formulas

    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
    SCRIPT
    -0.07
    erio
    -0.07
    ç»ĦæĪIJåijĺ
    -0.07
    _suffix
    -0.07
    æĹłéĹ»
    -0.07
    wiÄħ
    -0.07
    uil
    -0.07
     ëĭ¤
    -0.06
    Õ¹
    -0.06
    åŀĥåľ¾ç®±
    -0.06
    POSITIVE LOGITS
    irt
    0.07
    ä¿Ĺ
    0.07
    åĶ
    0.07
     appunto
    0.07
    çĶ±æĿ¥
    0.06
    RTOS
    0.06
    BOSE
    0.06
    ContentLoaded
    0.06
    ju
    0.06
    åħ¬ç§ģ
    0.06
    Activations Density 0.009%

    No Known Activations