© 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. 18750
    Prev
    Next
    INDEX
    Explanations

    "yes" or "no"

    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
    çŃł
    -0.08
    æĺŁçº§
    -0.08
    ç¼¥
    -0.07
    à¹Ģสà¸Ļ
    -0.07
    gers
    -0.07
    .signature
    -0.07
    amu
    -0.07
    ammers
    -0.07
    åħĭ森
    -0.07
    дÑı
    -0.07
    POSITIVE LOGITS
    åħ¶ä»ĸæĸ¹å¼ı
    0.08
    å¾Ĺä¸Ģ
    0.08
     outright
    0.08
    enco
    0.07
    æĹłæīĢè°ĵ
    0.07
    ä¸įäºĪ
    0.07
     indifference
    0.07
    åħ·ä½ĵæĥħåĨµ
    0.07
    èĩªå·±éĥ½
    0.07
    åħ¶ä»ĸçļĦ
    0.07
    Activations Density 0.072%

    No Known Activations