© 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. 2550
    Prev
    Next
    INDEX
    Explanations

    sequence convergence

    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
    andal
    -0.08
    #__
    -0.08
    ä¸ĢæĿ¡æĿ¡
    -0.08
    èģĶæĴŃ
    -0.08
    墨å°Ķ
    -0.08
    -0.08
    olib
    -0.07
    ï¾ī
    -0.07
    anner
    -0.07
    anny
    -0.07
    POSITIVE LOGITS
     incidental
    0.07
    éĶĻ误çļĦæĺ¯
    0.06
    ium
    0.06
    è¿Ļ个äºĭæĥħ
    0.06
    ä¸įæŃ£ç¡®çļĦæĺ¯
    0.06
     Department
    0.06
    rán
    0.06
    rá
    0.06
    кла
    0.06
    è®Ń
    0.05
    Activations Density 0.039%

    No Known Activations