© 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. 64001
    Prev
    Next
    INDEX
    Explanations

    approximations and estimates

    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
     allegedly
    -0.09
     supposedly
    -0.08
    çĽ¸å¯¹èĢĮè¨Ģ
    -0.08
    大èĩ´
    -0.08
     reportedly
    -0.07
    æĪĸå¤ļæĪĸå°ij
    -0.07
    æĩĤçļĦ
    -0.07
    åŃĺåľ¨ä¸ĢäºĽ
    -0.07
    å¤ļå¤ļå°ij
    -0.07
    ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸į
    0.07
    egel
    0.07
    UH
    0.07
    unsch
    0.07
    umper
    0.07
    ilit
    0.07
     güven
    0.07
    _but
    0.07
     Ain
    0.06
     banget
    0.06
    Activations Density 0.110%

    No Known Activations