© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58955
    Prev
    Next
    INDEX
    Explanations

    organizations and structures

    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
    Negative Logits
    urning
    -0.07
    åĩłæ¬¾
    -0.07
    áĥ¦
    -0.07
    ¢
    -0.07
    æŁIJä¸Ģ个
    -0.06
    å°±æĺ¯äºĨ
    -0.06
    çIJ³
    -0.06
    inqu
    -0.06
    å¤ļæĥ³
    -0.06
    orc
    -0.06
    POSITIVE LOGITS
     appunto
    0.10
    )!=
    0.08
     коÑĤоÑĢого
    0.08
    iba
    0.07
    .k
    0.07
     кÑģÑĤаÑĤи
    0.07
    èĢ³è¾¹
    0.07
    CALE
    0.07
    ä¸ĭåIJĮ
    0.07
    )||(
    0.07
    Activations Density 0.575%

    No Known Activations