© 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. 10155
    Prev
    Next
    INDEX
    Explanations

    numbers or codes

    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
    laat
    -0.07
    ResourceId
    -0.07
    andat
    -0.07
    ErrorHandler
    -0.07
    вÑĭв
    -0.07
     Volg
    -0.07
    ÑĢене
    -0.07
    autiful
    -0.07
    atlan
    -0.07
    enville
    -0.07
    POSITIVE LOGITS
    çݺ
    0.07
    ed
    0.07
    ERA
    0.07
    d
    0.07
    èĮĥåĽ´å¹¿
    0.06
    ter
    0.06
    icu
    0.06
    stoff
    0.06
    تش
    0.06
    ä¿Ń
    0.06
    Activations Density 0.023%

    No Known Activations