© 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. 32524
    Prev
    Next
    INDEX
    Explanations

    version control diffs

    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
    âĢ¦
    -0.06
    èıľçļĦ
    -0.06
    ent
    -0.06
    Ø«ÙĨ
    -0.06
    æ£Ĵ
    -0.06
    ibal
    -0.06
    æĪIJ交é¢Ŀ
    -0.06
    年头
    -0.06
     planta
    -0.06
    好å¿ĥæĥħ
    -0.06
    POSITIVE LOGITS
    åĨįæİ¥
    0.08
     Feinstein
    0.08
    UIS
    0.07
    gmail
    0.07
    uien
    0.07
    лизаÑĨии
    0.07
    ½Ķ
    0.07
    yli
    0.07
    nex
    0.07
    piel
    0.07
    Activations Density 0.003%

    No Known Activations