© 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. 28912
    Prev
    Next
    INDEX
    Explanations

    palpation and examination

    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
    åĨįæİ¥
    -0.08
    渲
    -0.08
    丧
    -0.07
    主ä½ĵå·¥ç¨ĭ
    -0.07
    å°ģ顶
    -0.07
    èĦ±ç¡«
    -0.07
    èĴ¸çħ®
    -0.07
     ricar
    -0.07
    éĿ¢åŃĶ
    -0.07
    aho
    -0.07
    POSITIVE LOGITS
     palp
    0.11
    åĩīçļĦ
    0.08
     inspection
    0.08
    æĮīåİĭ
    0.08
    æIJı
    0.08
     нада
    0.08
    触æĦŁ
    0.08
     examination
    0.08
     tactile
    0.08
    å¾Ĵæīĭ
    0.08
    Activations Density 0.065%

    No Known Activations