© 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. 42977
    Prev
    Next
    INDEX
    Explanations

    reciprocal relationships

    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
    å¤įåĪ¶æĪĸ
    -0.09
    æĪĸå¤ļæĪĸå°ij
    -0.08
    è¿ŀåIJĮ
    -0.08
    ä¸İä¼Ĺä¸įåIJĮ
    -0.08
    éĶĻ误æĪĸ
    -0.08
    ingerprint
    -0.08
    £¼
    -0.08
    umbuh
    -0.08
    à¹ģà¸ķ
    -0.07
    (vars
    -0.07
    POSITIVE LOGITS
     nhau
    0.11
    åīįèĢħ
    0.11
    åIJİèĢħ
    0.10
    äºĮèĢħ
    0.10
     بÙĬÙĨÙĩÙħا
    0.09
    两èĢħ
    0.08
     latter
    0.08
     elkaar
    0.07
     дÑĢÑĥг
    0.07
     Keduanya
    0.07
    Activations Density 0.138%

    No Known Activations