© 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. 2454
    Prev
    Next
    INDEX
    Explanations

    website or profile

    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
    swer
    -0.07
    æĺ¯éĿł
    -0.07
    atters
    -0.07
     thuáºŃt
    -0.06
    ést
    -0.06
    æĢ»ä¸įèĥ½
    -0.06
    å°Ĩä¸Ģ个
    -0.06
     Schwar
    -0.06
     panel
    -0.06
    å½Ŀ
    -0.06
    POSITIVE LOGITS
    inaire
    0.11
    inare
    0.08
    untu
    0.08
    ä¸įæĿ¥
    0.07
    inario
    0.07
    линд
    0.07
    inaires
    0.07
    ered
    0.07
    link
    0.07
     ÑĢед
    0.07
    Activations Density 0.102%

    No Known Activations