© 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. 1283
    Prev
    Next
    INDEX
    Explanations

    feasibility and alternatives

    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
    antina
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.07
    ÑģиÑħо
    -0.07
    åĽŀäºĭ
    -0.07
    oup
    -0.07
    modo
    -0.07
    YRO
    -0.06
    åħ¼æĢ»ç»ıçIJĨ
    -0.06
    asser
    -0.06
    OfWeek
    -0.06
    POSITIVE LOGITS
    ly
    0.09
    länder
    0.09
    ر
    0.08
    ieux
    0.08
    ilty
    0.08
    vre
    0.08
    Ĥ
    0.08
    iful
    0.08
    رض
    0.08
     Nunes
    0.08
    Activations Density 0.003%

    No Known Activations