© 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. 34800
    Prev
    Next
    INDEX
    Explanations

    robust method, business, findings, solutions

    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
    itsu
    -0.07
    opf
    -0.07
    యా
    -0.07
    à¸ŀิà¹Ģศษ
    -0.07
    icut
    -0.06
     Morris
    -0.06
    è¿ijå¹³
    -0.06
    obat
    -0.06
     Simpson
    -0.06
    ä¸ĢåįĬ
    -0.06
    POSITIVE LOGITS
    ë²Ķ
    0.08
    åĮħæĭ¬äºĨ
    0.08
    gst
    0.08
    åı¯éĿłçļĦ
    0.08
    chk
    0.07
     VALID
    0.07
    ç«Ń
    0.07
    -valid
    0.07
    严谨
    0.07
    èķĥ
    0.07
    Activations Density 0.001%

    No Known Activations