© 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. 3537
    Prev
    Next
    INDEX
    Explanations

    carcinomas or surgery

    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
    _ct
    -0.07
    Ctx
    -0.07
     att
    -0.07
    _logging
    -0.06
    CT
    -0.06
    ISTI
    -0.06
    ãĤĵãģ®
    -0.06
    ãĥ¼ãĥĬ
    -0.06
    igel
    -0.06
    onex
    -0.06
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.11
    æĪĸåħ¶å®ĥ
    0.09
    åį«ä¸ľ
    0.08
     or
    0.08
    æĪĸ缴æİ¥
    0.08
    posite
    0.07
    (or
    0.07
    æĪĸéĥ¨åĪĨ
    0.07
    uming
    0.07
    æĪĸ个人
    0.07
    Activations Density 0.535%

    No Known Activations