© 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. 29066
    Prev
    Next
    INDEX
    Explanations

    in fty

    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
    人åĪ°
    -0.08
    adak
    -0.08
    ovin
    -0.08
    رائ
    -0.08
    à¦ŀà§į
    -0.08
    à§įষ
    -0.08
    cie
    -0.07
    Å«d
    -0.07
    人åİ»
    -0.07
    uyá»ģn
    -0.07
    POSITIVE LOGITS
    fty
    0.07
    emani
    0.06
    çons
    0.06
    ä¸įæģ¯
    0.06
    esimal
    0.06
    à¤Ĥत
    0.06
    Ļ
    0.06
    ulton
    0.06
    çon
    0.06
    utz
    0.06
    Activations Density 0.002%

    No Known Activations