© 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. 46870
    Prev
    Next
    INDEX
    Explanations

    fourth point

    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
    jang
    -0.09
     FilePath
    -0.08
    Globals
    -0.07
    axter
    -0.07
    ä¹ĭ梦
    -0.07
     })(
    -0.07
    -</
    -0.07
     Bris
    -0.07
    reo
    -0.07
    passwd
    -0.07
    POSITIVE LOGITS
     involvement
    0.08
    ä»ĭåħ¥
    0.07
    POSIT
    0.07
    è¿Ļä¸ī
    0.07
    åŃ¦ä¹łä¸İ
    0.07
    ä¸İåīį
    0.07
    åĸľæĢĴ
    0.07
    OCO
    0.07
    _extension
    0.06
     ketiga
    0.06
    Activations Density 0.007%

    No Known Activations