© 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. 24499
    Prev
    Next
    INDEX
    Explanations

    stages beginning

    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¿ĽéĢĢ
    -0.07
    æijĨæĶ¾åľ¨
    -0.07
    åIJµéĹ¹
    -0.06
    姿
    -0.06
    åħį
    -0.06
    æĶ¶åıij
    -0.06
    terminated
    -0.06
    _EV
    -0.06
    åĸľæĢĴåĵĢä¹IJ
    -0.06
    jam
    -0.06
    POSITIVE LOGITS
    å¼Ģå§ĭåĩºçİ°
    0.13
     본격
    0.13
    并å¼Ģå§ĭ
    0.13
     begins
    0.11
    å¼Ģå§ĭ
    0.11
     begin
    0.10
    éĢIJæ¸IJ
    0.10
     beginning
    0.10
    éĥ½å¼Ģå§ĭ
    0.10
     begun
    0.09
    Activations Density 0.021%

    No Known Activations