© 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. 3621
    Prev
    Next
    INDEX
    Explanations

    \int_

    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
    ases
    -0.08
    adis
    -0.07
    å·´å¡ŀ
    -0.07
    iminal
    -0.07
    สิà¹īà¸Ļ
    -0.07
    asai
    -0.07
    ä¸įåıĬå¾ħ
    -0.07
    管好
    -0.07
    åĴ«
    -0.07
    á»iji
    -0.06
    POSITIVE LOGITS
    endre
    0.07
    çıįçıł
    0.07
    cki
    0.07
     иÑģÑĤо
    0.07
    ieben
    0.07
     Pearce
    0.07
     má»ı
    0.07
    ίÏĥ
    0.07
    _iterations
    0.07
    clado
    0.07
    Activations Density 0.004%

    No Known Activations