© 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. 21089
    Prev
    Next
    INDEX
    Explanations

    maximum limits

    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
    rish
    -0.08
    attel
    -0.08
     Tatsache
    -0.07
     arras
    -0.07
    Synopsis
    -0.07
    enzo
    -0.07
    özÅij
    -0.07
    bons
    -0.07
    ÙĦÙĬب
    -0.07
    ابÛĮ
    -0.07
    POSITIVE LOGITS
    IMUM
    0.13
    imum
    0.12
    éĻIJ度
    0.11
     tolerated
    0.11
     allowable
    0.11
     allowed
    0.11
    ä¸įèĥ½è¶ħè¿ĩ
    0.10
    éĻIJ度çļĦ
    0.10
     permissible
    0.10
    /max
    0.10
    Activations Density 0.045%

    No Known Activations