© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20720
    Prev
    Next
    INDEX
    Explanations

    U-shaped and V-shaped forms

    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
    æĥ³æĸ¹
    -0.08
    flies
    -0.08
    ä¸įä¹ı
    -0.07
    åIJŀåIJIJ
    -0.07
    å±ĤçļĦ
    -0.07
    å±Ĥ
    -0.06
     Clair
    -0.06
     bust
    -0.06
    auh
    -0.06
    eding
    -0.06
    POSITIVE LOGITS
    -shaped
    0.10
    ạng
    0.08
    relude
    0.08
     Gusta
    0.07
    å¼ıçļĦ
    0.07
    schau
    0.07
    euw
    0.07
    缺ä¸Ģ
    0.07
    à¤ķार
    0.07
    çĭĹä»Ķ
    0.07
    Activations Density 0.026%

    No Known Activations