© 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. 1660
    Prev
    Next
    INDEX
    Explanations

    listing specific items

    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
     Savage
    -0.08
     przecież
    -0.08
    evi
    -0.07
    á»Ļp
    -0.07
    мина
    -0.07
    没æľīåĬŀæ³ķ
    -0.07
    itó
    -0.07
    ÄĻt
    -0.07
    inqui
    -0.07
    isci
    -0.07
    POSITIVE LOGITS
    wijk
    0.07
    uchy
    0.07
    matic
    0.07
    éķ¿çĽ¸
    0.07
    ier
    0.07
    ful
    0.07
    çĦ¶çļĦ
    0.06
    大éģĵ
    0.06
    der
    0.06
    ud
    0.06
    Activations Density 0.582%

    No Known Activations