© 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. 44907
    Prev
    Next
    INDEX
    Explanations

    html attribute quotes

    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
    鸳鸯
    -0.08
    è¡¥åĬ©è´¹
    -0.08
    kow
    -0.08
    haut
    -0.07
    å¸Īé£İ
    -0.07
    Separated
    -0.07
    picker
    -0.07
    å©Ĩ
    -0.07
    оÑĩе
    -0.07
    emony
    -0.07
    POSITIVE LOGITS
    ogie
    0.08
    ampa
    0.08
    åħ¨èº«
    0.07
    ãĤ·ãĤ§ãĤ¢
    0.07
    ouer
    0.07
    çĻ¾åĪĨä¹ĭ
    0.07
    igator
    0.07
    opr
    0.07
    oyer
    0.07
    æ°ijçĶ¨
    0.06
    Activations Density 0.067%

    No Known Activations