© 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. 64519
    Prev
    Next
    INDEX
    Explanations

    information requests and answers

    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
     بشÙĥÙĦ
    -0.07
    æľºçŃī
    -0.07
    ç±»çŃī
    -0.07
    å«Į
    -0.07
     themselves
    -0.07
    们
    -0.06
    ionalmente
    -0.06
    åħ¬åı¸çŃī
    -0.06
    深水
    -0.06
    _FF
    -0.06
    POSITIVE LOGITS
    ึà¸ĩ
    0.07
    ä¸į误
    0.07
    кÑĥпа
    0.07
    æģ©æĸ¯
    0.07
    éģ¿åħįåĽł
    0.07
    _creator
    0.07
    ç¥ŀä¹ĭ
    0.07
    åıĤä¸İåĪ°
    0.06
    ä¸Ĭæ·»
    0.06
    æĶ¹è§Ĥ
    0.06
    Activations Density 0.012%

    No Known Activations