© 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. 3259
    Prev
    Next
    INDEX
    Explanations

    date, name, false, a

    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
    å½ĵä¹ĭ
    -0.07
    ect
    -0.07
    ModuleName
    -0.07
    åĩĿ
    -0.07
    峪
    -0.06
    ael
    -0.06
    .exclude
    -0.06
    ä¸įäºĨå¤ļä¹ħ
    -0.06
    ators
    -0.06
    èĥŀ
    -0.06
    POSITIVE LOGITS
    kép
    0.08
    è´¢è¿IJ
    0.07
    licer
    0.07
    CTYPE
    0.07
    ified
    0.07
    issance
    0.07
    аниз
    0.07
    orium
    0.07
    iversal
    0.07
    compressed
    0.07
    Activations Density 0.001%

    No Known Activations