© 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. 22353
    Prev
    Next
    INDEX
    Explanations

    unless otherwise noted or stated

    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
    äºĨäºĽ
    -0.07
    ä¸Ģ个éĩįè¦ģ
    -0.07
    çĸijä¼¼è¿Ŀè§Ħ
    -0.07
    oje
    -0.07
    æĭŁ
    -0.07
    à¹ĩ
    -0.07
    ä½įç½®ä¸Ĭ
    -0.07
    åĪĿæľŁçļĦ
    -0.07
    reu
    -0.07
     Closet
    -0.07
    POSITIVE LOGITS
     otherwise
    0.13
    otherwise
    0.11
     Otherwise
    0.10
    åIJ¦åĪĻ
    0.10
     autrement
    0.09
     elsewhere
    0.08
     OTHERWISE
    0.08
    Otherwise
    0.08
     overrides
    0.08
     altrimenti
    0.07
    Activations Density 0.125%

    No Known Activations