© 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. 20566
    Prev
    Next
    INDEX
    Explanations

    followed by description or link

    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
    ornado
    -0.08
    彿
    -0.07
     âĻ
    -0.07
    å¾ĪèĪĴæľį
    -0.07
    ertools
    -0.07
    ãģŁãģ£ãģ¦
    -0.06
    -bodied
    -0.06
    å¼ģ
    -0.06
    rak
    -0.06
    æĺ¥é£İ
    -0.06
    POSITIVE LOGITS
    hein
    0.08
    åħįè´¹éĺħ读
    0.07
    åĪ°å¤§
    0.07
    éĿŀåIJĮ
    0.06
    Úij
    0.06
    osa
    0.06
    æł¼æĭī
    0.06
    èĮ¨
    0.06
    eed
    0.06
    ialis
    0.06
    Activations Density 0.225%

    No Known Activations