© 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. 14259
    Prev
    Next
    INDEX
    Explanations

    de JVM, memória, filme

    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
    ly
    -0.13
    lah
    -0.12
    nya
    -0.11
    çļĦ
    -0.09
    ä¸Ģ个
    -0.09
    raries
    -0.09
    d
    -0.09
    ä¸Ń
    -0.08
    ÙĩÙħ
    -0.08
    se
    -0.08
    POSITIVE LOGITS
    Ø©
    0.11
     cÄĥtre
    0.10
    Ïĥη
    0.10
    plx
    0.09
    ç¯ĩä¸Ģ
    0.09
    боÑĢÑĭ
    0.09
    åIJĪåIJĮæŶ
    0.09
    precated
    0.09
    ä½įçļĦ
    0.09
    äºĨ好åĩł
    0.09
    Activations Density 0.026%

    No Known Activations