© 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. 55573
    Prev
    Next
    INDEX
    Explanations

    end user requests

    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
    à¥įलà¥Ģ
    -0.08
    ØŃÙĪ
    -0.08
    Ŀ
    -0.08
    åijĹ
    -0.07
     appunto
    -0.07
    à¸Ńะà¹Ħรà¸ļà¹īาà¸ĩ
    -0.07
    achi
    -0.07
     perspectiv
    -0.07
    à¹ģà¸Ī
    -0.07
    mani
    -0.07
    POSITIVE LOGITS
    undy
    0.07
    opper
    0.07
    uple
    0.06
    isit
    0.06
    ikker
    0.06
    illante
    0.06
    å¾·åĪ©
    0.06
    matic
    0.06
    å¥ij
    0.06
     Wilkinson
    0.06
    Activations Density 0.395%

    No Known Activations