© 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. 27699
    Prev
    Next
    INDEX
    Explanations

    agreements

    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
    åĩĨå¦Īå¦Ī
    -0.08
     Bucc
    -0.08
    åŃļ
    -0.08
    į¼
    -0.07
     gala
    -0.07
    stag
    -0.07
    лиÑı
    -0.07
    uye
    -0.07
    å¹´åºķåīį
    -0.07
    erus
    -0.07
    POSITIVE LOGITS
    raz
    0.07
    ç»ĪæĹ¥
    0.07
     positivity
    0.07
    abat
    0.07
     everywhere
    0.07
    -basic
    0.06
    æŀĦéĢł
    0.06
     quadratic
    0.06
    é©»
    0.06
    èĴĤ
    0.06
    Activations Density 0.006%

    No Known Activations