© 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. 50680
    Prev
    Next
    INDEX
    Explanations

    form + variable

    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
     supra
    -0.07
    çĽijäºĭä¼ļ
    -0.07
     intens
    -0.07
    Lic
    -0.06
     Tup
    -0.06
    æ´»å¾Ĺ
    -0.06
    åķĨä¼ļ
    -0.06
    ä¸ĢçĶŁçļĦ
    -0.06
     Mitt
    -0.06
     laps
    -0.06
    POSITIVE LOGITS
    æł¼å¼ı
    0.11
    æł¼å¼ıçļĦ
    0.11
     format
    0.10
     formats
    0.09
    å½¢å¼ı
    0.08
    rew
    0.08
    -compatible
    0.08
    bereit
    0.08
    -ready
    0.08
    compatible
    0.08
    Activations Density 0.011%

    No Known Activations