© 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. 23698
    Prev
    Next
    INDEX
    Explanations

    page, paste this HTML

    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
    æĻĵ
    -0.07
     hi
    -0.06
     sk
    -0.06
    天éĻħ
    -0.06
    éĿĸ
    -0.06
     Rap
    -0.06
    SK
    -0.06
    欣
    -0.06
    CB
    -0.06
     Alg
    -0.06
    POSITIVE LOGITS
    æķĻäºİ
    0.09
    ProcessEvent
    0.09
    achs
    0.08
     reservados
    0.08
    éĥ¨ç»ıçIJĨ
    0.08
    trup
    0.08
    èĩ³åħ³
    0.08
    remium
    0.08
    rega
    0.08
    errar
    0.08
    Activations Density 0.009%

    No Known Activations