© 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. 28668
    Prev
    Next
    INDEX
    Explanations

    information and related concepts

    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
    éĢļ天
    -0.07
    å¸ĥæĸ¯
    -0.07
    ysi
    -0.07
    请çĻ»å½ķ
    -0.06
    缸åħ³éĹ®çŃĶ
    -0.06
    chetta
    -0.06
    _tensors
    -0.06
    åıªæľīä¸Ģ次
    -0.06
     Metropol
    -0.06
    unar
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.08
    ä¸ĭåIJĮ
    0.08
    urtle
    0.07
     insomma
    0.07
    obuf
    0.07
    ago
    0.07
     Schönh
    0.07
    缶
    0.07
    çĶļèĩ³è¿ĺ
    0.07
    kwargs
    0.06
    Activations Density 0.796%

    No Known Activations