© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11870
    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
     leist
    -0.07
    人è´Ńä¹°
    -0.07
    CAF
    -0.07
    eref
    -0.06
    æ¡¥
    -0.06
     ÐĿали
    -0.06
    _migration
    -0.06
    spec
    -0.06
    CS
    -0.06
     Menj
    -0.06
    POSITIVE LOGITS
    obo
    0.08
     âĸ·
    0.07
    unti
    0.07
    ç§ķ
    0.07
    gether
    0.07
    æ´¾éĢģ
    0.07
    quential
    0.07
    alue
    0.07
    深信
    0.07
    ropy
    0.06
    Activations Density 0.000%

    No Known Activations