© 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. 18577
    Prev
    Next
    INDEX
    Explanations

    example, for, given, input, output

    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
    okol
    -0.06
    /utility
    -0.06
     Candid
    -0.06
    麻èĬ±
    -0.06
     buz
    -0.06
    æ¸ħäºĨ
    -0.06
    ritic
    -0.06
    ืà¸Ńà¸ģ
    -0.06
    -org
    -0.06
     Comparable
    -0.06
    POSITIVE LOGITS
    aced
    0.08
    andt
    0.07
    exampleInput
    0.07
    astro
    0.07
     HelloWorld
    0.07
    _mini
    0.07
    _REPORT
    0.07
    iaire
    0.07
     Envi
    0.07
     emot
    0.07
    Activations Density 0.006%

    No Known Activations