© 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. 28008
    Prev
    Next
    INDEX
    Explanations

    organizational sectors

    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¸įèĩ³
    -0.08
    راÙħ
    -0.07
    èĬĤçļĦ
    -0.07
     REQ
    -0.06
    èĬĤ
    -0.06
    artz
    -0.06
    åľ¨çĽ®
    -0.06
    ستر
    -0.06
    amber
    -0.06
    ekan
    -0.06
    POSITIVE LOGITS
    æŀŃ
    0.08
    plier
    0.08
    综åIJĪæĢ§
    0.07
    åħ¸åŀĭçļĦ
    0.07
    /Main
    0.07
    AYA
    0.07
    ç»İ
    0.07
    oplevel
    0.07
    rossover
    0.07
    æ¾
    0.07
    Activations Density 0.151%

    No Known Activations