© 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. 7205
    Prev
    Next
    INDEX
    Explanations

    rounding decimal places

    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
    aS
    -0.07
    chor
    -0.07
    jada
    -0.07
    iori
    -0.07
    åıĪåĪ°
    -0.06
    裳
    -0.06
    urat
    -0.06
    FS
    -0.06
    åŁĭä¼ı
    -0.06
    æĬĬ好
    -0.06
    POSITIVE LOGITS
    asti
    0.08
    ussen
    0.08
     rives
    0.08
     mest
    0.07
    çݰ象
    0.07
    å¿ĺä¸įäºĨ
    0.07
    lanz
    0.07
    zend
    0.07
    icz
    0.07
    istani
    0.07
    Activations Density 0.019%

    No Known Activations