© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2772
    Prev
    Next
    INDEX
    Explanations

    boolean checks

    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
    ())->
    -0.08
    zien
    -0.08
     newData
    -0.07
    /extensions
    -0.07
    vette
    -0.07
    --,
    -0.07
    åĽ½éŨ
    -0.07
    /rc
    -0.07
     Garner
    -0.07
     Äijá»ĵi
    -0.07
    POSITIVE LOGITS
    contest
    0.07
    æĮ½
    0.07
    ecas
    0.07
     contested
    0.06
    ikum
    0.06
    Äı
    0.06
     netr
    0.06
    áĢĻ
    0.06
    ç´¯
    0.06
     sinon
    0.06
    Activations Density 0.030%

    No Known Activations