© 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. 64516
    Prev
    Next
    INDEX
    Explanations

    country names

    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
    åıĭ好
    -0.06
    afx
    -0.06
    zat
    -0.06
    -0.06
    å¾Ļ
    -0.06
    ýt
    -0.06
     affirmation
    -0.06
    É
    -0.06
    notated
    -0.06
    entic
    -0.06
    POSITIVE LOGITS
    à¹īว
    0.09
    ä¸ĢåºĶ
    0.07
    _sections
    0.07
    opolitan
    0.07
    olin
    0.07
    ä¸ĥåįģäºĮ
    0.07
     Geren
    0.07
    à¹Ģลà¸Ļ
    0.07
    γγ
    0.07
    dds
    0.07
    Activations Density 0.968%

    No Known Activations