© 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. 41728
    Prev
    Next
    INDEX
    Explanations

    scale up or down

    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
    çİĩé«ĺ
    -0.08
    rens
    -0.08
    ¼
    -0.08
    requ
    -0.08
    zelf
    -0.07
    اث
    -0.07
    shire
    -0.07
    สà¸ĩà¸Ħà¹Į
    -0.07
    icus
    -0.07
    аем
    -0.07
    POSITIVE LOGITS
    inheit
    0.10
    mÃ¤ÃŁig
    0.09
     بÙĨدÛĮ
    0.09
    er
    0.09
    enburg
    0.08
    ToFit
    0.08
    ë§ģ
    0.08
    à¹Ħหà¸Ļ
    0.08
    nect
    0.08
    orpion
    0.08
    Activations Density 0.039%

    No Known Activations