© 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. 39336
    Prev
    Next
    INDEX
    Explanations

    document structure and content

    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
    è®©æĽ´å¤ļ读èĢħ
    -0.08
    åľ¨éĤ£éĩĮ
    -0.07
    edy
    -0.07
    è·»
    -0.06
    ToArray
    -0.06
    toArray
    -0.06
    éĤ£éĩĮ
    -0.06
    arka
    -0.06
    quiv
    -0.06
    åĬłåĭĴ
    -0.06
    POSITIVE LOGITS
    ubo
    0.09
    oja
    0.07
    ESO
    0.07
    otan
    0.07
    ç§įçļĦ
    0.06
    ìłĢ
    0.06
    種種
    0.06
     various
    0.06
    avar
    0.06
    åĨįä¸Ģ次
    0.06
    Activations Density 0.166%

    No Known Activations