© 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. 60887
    Prev
    Next
    INDEX
    Explanations

    Bikers, Anniversary, delivery devices, logic devices

    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
    amaan
    -0.06
    icker
    -0.06
     اÙĦÙĦÙĩÙı
    -0.06
    ä»·æł¼æĮĩæķ°
    -0.06
    èĻ±
    -0.06
    kok
    -0.06
     Alfon
    -0.06
    è¿
    -0.06
    æĢ¯
    -0.06
    @s
    -0.06
    POSITIVE LOGITS
    lesh
    0.07
    æī£
    0.07
     bât
    0.07
     appunto
    0.06
    วิà¸Ļ
    0.06
    rawat
    0.06
    omás
    0.06
    agod
    0.06
     Pen
    0.06
     pen
    0.06
    Activations Density 1.945%

    No Known Activations