© 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. 40715
    Prev
    Next
    INDEX
    Explanations

    numeric citations and identifiers

    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
    OSH
    -0.08
    orme
    -0.07
    éĽħå®ī
    -0.07
    igente
    -0.07
    æ¥Ń
    -0.07
    ÏģοÏĤ
    -0.07
    ÐľÐŁ
    -0.07
    ozy
    -0.06
    imps
    -0.06
    quo
    -0.06
    POSITIVE LOGITS
    驻马
    0.10
    aring
    0.07
    ült
    0.07
     Casal
    0.07
    åĦ¿çļĦ
    0.07
    eller
    0.07
    ×¢×Ķ
    0.06
    ungi
    0.06
    arang
    0.06
    .lu
    0.06
    Activations Density 0.035%

    No Known Activations