© 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. 30398
    Prev
    Next
    INDEX
    Explanations

    genes, patients, cases, flow

    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
    agi
    -0.08
     Agen
    -0.07
    ittest
    -0.07
    éĽĦé¹°
    -0.07
    HW
    -0.07
    IfNeeded
    -0.06
    chaft
    -0.06
    ער
    -0.06
    çļĦåIJĮæŶ
    -0.06
    PIO
    -0.06
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.08
     dara
    0.07
    arate
    0.07
    inely
    0.07
    ofs
    0.07
    angkan
    0.06
    ably
    0.06
    's
    0.06
    æĿ¥ä¹ĭ
    0.06
    era
    0.06
    Activations Density 1.371%

    No Known Activations