© 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. 65405
    Prev
    Next
    INDEX
    Explanations

    number followed by abbreviation

    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
    .complete
    -0.07
    nes
    -0.07
    åĩłä¹İæĺ¯
    -0.07
    witter
    -0.07
    ynos
    -0.07
    yne
    -0.06
     gradu
    -0.06
    =>$
    -0.06
    _PKT
    -0.06
    åĪĴ线
    -0.06
    POSITIVE LOGITS
    CTX
    0.07
    ald
    0.07
    avis
    0.07
    çĦ¶
    0.07
    è¿Ļ个éģĵçIJĨ
    0.07
    oksi
    0.07
    _guard
    0.07
    åĬªåĬĽå¥ĭæĸĹ
    0.07
    acon
    0.07
    åĴĮç²¾ç¥ŀ
    0.06
    Activations Density 0.007%

    No Known Activations