© 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. 50995
    Prev
    Next
    INDEX
    Explanations

    degrees or numbers

    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
    æµģéĩıçļĦ
    -0.09
    IFIER
    -0.08
    alet
    -0.08
    天ä¸ĭçļĦ
    -0.08
    ×Ļר×ķת
    -0.08
    yst
    -0.08
    ocache
    -0.07
    ysten
    -0.07
     verme
    -0.07
    翼翼
    -0.07
    POSITIVE LOGITS
    abu
    0.07
    æķ£
    0.06
    è´¥
    0.06
    åĨħ
    0.06
    oscope
    0.06
    大ä¼ļ
    0.06
    askell
    0.06
    åIJĽ
    0.06
    lom
    0.06
    omb
    0.06
    Activations Density 0.001%

    No Known Activations