© 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. 16670
    Prev
    Next
    INDEX
    Explanations

    direct and direct-to

    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
    дино
    -0.08
    illot
    -0.08
    zbek
    -0.08
    -0.08
    ä¹ĭæģĭ
    -0.08
    mehr
    -0.07
    trys
    -0.07
    ardu
    -0.07
    unce
    -0.07
    NewLabel
    -0.07
    POSITIVE LOGITS
    ivity
    0.10
    ly
    0.10
    rix
    0.09
    cly
    0.09
    rices
    0.09
    ampton
    0.09
    ives
    0.08
    ÃŃsimo
    0.08
    ìłģìĿ¸
    0.08
    issima
    0.08
    Activations Density 0.062%

    No Known Activations