© 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. 13121
    Prev
    Next
    INDEX
    Explanations

    down to

    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
    atos
    -0.08
    ourir
    -0.07
    åĪļ好
    -0.07
    æį¢æĿ¥çļĦ
    -0.07
    ocat
    -0.07
     hiếm
    -0.07
    triz
    -0.07
    ibu
    -0.07
    ẻo
    -0.07
    ic
    -0.07
    POSITIVE LOGITS
    æĺ¯åIJ¦åŃĺåľ¨
    0.09
     whether
    0.09
    FUNC
    0.07
    æĺ¯åIJ¦ä¸º
    0.07
    æĺ¯åIJ¦åľ¨
    0.07
    å¦Ĥä½ķçľĭå¾ħ
    0.07
    whether
    0.07
     Concent
    0.07
    æī¾åĩº
    0.07
    xic
    0.06
    Activations Density 0.011%

    No Known Activations