© 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. 32759
    Prev
    Next
    INDEX
    Explanations

    number of

    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
    minster
    -0.09
    OrElse
    -0.08
    à¸ģระà¸Ĺัà¹Īà¸ĩ
    -0.08
    ëĦIJ
    -0.08
    ï¸İ
    -0.08
    ฺ
    -0.08
    å§ĭèĩ³ç»Ī
    -0.08
    ullivan
    -0.07
    éĩij森
    -0.07
     ê·¸ëŁ¬ë©´ìĦľ
    -0.07
    POSITIVE LOGITS
    oft
    0.10
    hood
    0.09
    drig
    0.09
    zinho
    0.08
    er
    0.08
    lijke
    0.08
    folge
    0.08
    cy
    0.08
    ãģĵãģª
    0.08
    ä¸Ģæķ°
    0.08
    Activations Density 0.078%

    No Known Activations