© 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. 3548
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and programming constructs

    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
    regor
    -0.08
    顺é£İ
    -0.07
    ertype
    -0.07
    ovar
    -0.07
    ergen
    -0.07
    etas
    -0.07
    æīİ
    -0.07
    beit
    -0.07
    accio
    -0.07
    ostas
    -0.07
    POSITIVE LOGITS
    Mappings
    0.08
    _mappings
    0.07
    æĺłå°Ħ
    0.07
    HEADER
    0.07
    æĪIJäº¤ä»·æł¼
    0.06
    ujan
    0.06
    ============
    0.06
    MIT
    0.06
    lan
    0.06
     disposer
    0.06
    Activations Density 0.177%

    No Known Activations