© 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. 31338
    Prev
    Next
    INDEX
    Explanations

    operator

    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
    æĮºèº«
    -0.08
    ä¸ĢåĪĻ
    -0.07
    åı¯çĩĥ
    -0.07
     decode
    -0.07
    éķ¿ç¯ĩ
    -0.07
    olla
    -0.07
    åĩī
    -0.06
     decoded
    -0.06
     кем
    -0.06
    decoded
    -0.06
    POSITIVE LOGITS
     operator
    0.12
     operators
    0.12
     Operator
    0.11
    æĵįä½ľçļĦ
    0.11
     Operators
    0.10
    operator
    0.09
    -operator
    0.09
    /operator
    0.09
    Operator
    0.09
    .operator
    0.09
    Activations Density 0.004%

    No Known Activations