© 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. 26443
    Prev
    Next
    INDEX
    Explanations

    command line results

    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
    ertz
    -0.07
    æŀĦ
    -0.07
    .ly
    -0.07
    .parentNode
    -0.06
    ++;
    -0.06
    emel
    -0.06
    æŀĦåĽ¾
    -0.06
    .TryParse
    -0.06
    mailto
    -0.06
    elos
    -0.06
    POSITIVE LOGITS
    çµIJæŀľ
    0.07
    æıIJ示信æģ¯
    0.07
    bling
    0.07
    athed
    0.07
    pong
    0.07
     accomplished
    0.07
    Cached
    0.07
    оба
    0.07
    anggil
    0.07
    ylim
    0.06
    Activations Density 0.015%

    No Known Activations