© 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. 27173
    Prev
    Next
    INDEX
    Explanations

    definitions and terms

    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
    orit
    -0.07
    usin
    -0.07
    Ïĥμα
    -0.07
    contents
    -0.06
    rette
    -0.06
    åĨħå®¹è¿Ľè¡Į
    -0.06
    .must
    -0.06
     abon
    -0.06
    ÑĦон
    -0.06
    è°ļ
    -0.06
    POSITIVE LOGITS
     Definitions
    0.09
     definitions
    0.09
    ä¸Ģå¾ĭ
    0.09
    Definitions
    0.09
     Defined
    0.08
     defined
    0.08
     Terms
    0.08
    éĿŀ常æĦŁè°¢
    0.08
    defined
    0.08
    ÏĦαν
    0.08
    Activations Density 0.063%

    No Known Activations