© 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. 19543
    Prev
    Next
    INDEX
    Explanations

    rules, laws, and compliance terms

    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
    ISMO
    -0.08
    orado
    -0.08
     Radical
    -0.08
    orton
    -0.08
    ambul
    -0.07
    å®ĥä¸İ
    -0.07
    ajah
    -0.07
    olim
    -0.07
    oose
    -0.07
    -cont
    -0.07
    POSITIVE LOGITS
    èĢĮè¡Į
    0.08
    pliant
    0.07
    åľ¨èº«
    0.07
    èĢĮåĩº
    0.07
    èĢĮåĬ¨
    0.07
    寸
    0.06
    çļĦåīįæıIJä¸ĭ
    0.06
    åĴĮçī¹çĤ¹
    0.06
    ä¸įèµ°
    0.06
    ä¸Ķåľ¨
    0.06
    Activations Density 0.148%

    No Known Activations