© 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. 64890
    Prev
    Next
    INDEX
    Explanations

    minimum requirements

    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
    ä¾
    -0.07
    isht
    -0.07
    åĨħåIJij
    -0.07
    æ¿
    -0.07
    BRE
    -0.07
    èĭ±ä¿Ĭ
    -0.07
    runtime
    -0.06
    ä¸ŃåĽ½ç«Ļ
    -0.06
    å¥Ħ
    -0.06
    æİĸ
    -0.06
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.10
     accumulating
    0.09
    累积
    0.09
    สะสม
    0.08
     accumul
    0.08
    累计
    0.08
    积累
    0.08
     acum
    0.08
    abin
    0.08
    accum
    0.08
    Activations Density 0.029%

    No Known Activations