© 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. 30817
    Prev
    Next
    INDEX
    Explanations

    alphanumeric characters and symbols

    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
    azes
    -0.07
    ottes
    -0.07
    ¬
    -0.07
    å¸ĪèĮĥåѦéĻ¢
    -0.07
    _FC
    -0.07
    人æ°ijåĮ»éĻ¢
    -0.07
    ures
    -0.06
    obel
    -0.06
    天ä¸ĭ
    -0.06
    åĽ¢æĢ»æĶ¯
    -0.06
    POSITIVE LOGITS
    oke
    0.08
    orden
    0.07
    賦
    0.07
     Bundy
    0.07
    ++++
    0.07
    éĩijéĵ¶
    0.06
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.06
     allemaal
    0.06
    alli
    0.06
    ä¹Łè·Ł
    0.06
    Activations Density 0.041%

    No Known Activations