© 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. 15821
    Prev
    Next
    INDEX
    Explanations

    four-time champion or medalist

    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
    awi
    -0.08
    iverse
    -0.08
    ë¡ľëĤĺ
    -0.07
    inality
    -0.07
    ecat
    -0.07
    vider
    -0.07
    iš
    -0.07
    ë¶Ģë¡ľ
    -0.07
    TMP
    -0.07
    ×ķ׳×Ķ
    -0.07
    POSITIVE LOGITS
    çij¾
    0.07
    åºĵ
    0.07
    éļĨ
    0.06
    稿
    0.06
    ç©·
    0.06
    KU
    0.06
    éĿ¢
    0.06
    ehen
    0.06
    å±ķå¼Ģ
    0.06
    lott
    0.06
    Activations Density 0.471%

    No Known Activations