© 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. 60498
    Prev
    Next
    INDEX
    Explanations

    cellular or tumorous cells

    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
     historically
    -0.08
     certain
    -0.07
     certos
    -0.07
     Siv
    -0.07
     ciertos
    -0.07
     certas
    -0.07
     Certain
    -0.07
    ullet
    -0.07
    åĽ¾çīĩæĪĸ
    -0.07
    è¶Ĭæĥ³
    -0.07
    POSITIVE LOGITS
     evidently
    0.11
    æĺ¾çĦ¶æĺ¯
    0.10
    ä¼¼ä¹İ
    0.09
    ä¼¼ä¹İæĺ¯
    0.09
    æĺİæĺ¾çļĦ
    0.09
     offenbar
    0.09
     apparently
    0.09
    æĺİæĺ¾
    0.09
     presumably
    0.08
    ä¼¼ä¹İåľ¨
    0.08
    Activations Density 0.746%

    No Known Activations