© 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. 27687
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ource
    -0.07
    -sdk
    -0.07
    æºIJ
    -0.07
    atorial
    -0.06
    为æ°ij
    -0.06
    åIJİåı°
    -0.06
    apid
    -0.06
    å®ļ为
    -0.06
    åIJİåı°åĽŀå¤į
    -0.06
     header
    -0.06
    POSITIVE LOGITS
    麻
    0.08
    åħ¶æŀĹ
    0.07
    娥
    0.07
    _CURRENT
    0.07
    uggy
    0.07
     Souls
    0.07
    ppy
    0.07
    ä¸Ģæķ´
    0.07
    sell
    0.07
    微信æī«çłģ
    0.07
    Activations Density 0.050%

    No Known Activations