© 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. 49469
    Prev
    Next
    INDEX
    Explanations

    math/code delimiters or keywords

    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
    irti
    -0.07
    çŃīåIJĦæĸ¹éĿ¢
    -0.06
    æŀ¶ä¸Ĭ
    -0.06
    thesize
    -0.06
    æĮīçħ§è§Ħå®ļ
    -0.06
    çĽĸä¸Ĭ
    -0.06
    åĴĮåĪ«äºº
    -0.06
    iese
    -0.06
    å°Ĩ该
    -0.06
    éķ¿æĮīè¯ĨåĪ«äºĮç»´çłģ
    -0.06
    POSITIVE LOGITS
    大家éĥ½å¾Ī
    0.08
    _NB
    0.08
    гÑĥÑĢ
    0.08
    auge
    0.08
    ropolit
    0.07
     itself
    0.07
    _PT
    0.07
    жеÑĢ
    0.07
     pouc
    0.07
    rosse
    0.07
    Activations Density 0.012%

    No Known Activations