© 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. 17618
    Prev
    Next
    INDEX
    Explanations

    text following "The" or "A"

    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
    ulti
    -0.08
    ongyang
    -0.07
    unctuation
    -0.07
    URNS
    -0.07
    CLUDED
    -0.07
    Ùĥر
    -0.07
    notated
    -0.07
    xCA
    -0.07
    riangle
    -0.07
     despla
    -0.07
    POSITIVE LOGITS
    eden
    0.07
    agu
    0.07
    YY
    0.07
    eward
    0.06
    YW
    0.06
    ç²Ĺ
    0.06
    å¿»
    0.06
    YN
    0.06
     Shall
    0.06
    ä¸ĢäºĮ
    0.06
    Activations Density 0.071%

    No Known Activations