© 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. 38068
    Prev
    Next
    INDEX
    Explanations

    phone numbers and figures

    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
    eka
    -0.07
    lings
    -0.07
    os
    -0.07
    arn
    -0.07
    ling
    -0.07
    izer
    -0.07
    ellas
    -0.07
    ance
    -0.07
    icks
    -0.07
    ery
    -0.07
    POSITIVE LOGITS
    isie
    0.08
    æĮ
    0.08
    StackSize
    0.08
    bstract
    0.07
    aufen
    0.07
     onDataChange
    0.07
    使çĶ¨éģĵåħ·
    0.07
     //--------------------------------
    0.07
    Õ®
    0.07
    -**
    0.07
    Activations Density 0.010%

    No Known Activations