© 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. 7551
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çݺ
    -0.07
    æĸĩåijĺ
    -0.07
    课æŶ
    -0.07
    ifter
    -0.07
    ipher
    -0.06
    ocal
    -0.06
    _BAL
    -0.06
    ëĿ¼ìļ°
    -0.06
    è¿«
    -0.06
    nell
    -0.06
    POSITIVE LOGITS
    yac
    0.08
    quier
    0.07
    omatic
    0.07
    ä¸Ĭ大
    0.07
    åĩĮäºij
    0.07
    ENTOS
    0.07
    æĢ¯
    0.07
    ض
    0.07
    ieee
    0.07
    mera
    0.07
    Activations Density 0.000%

    No Known Activations