© 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. 38832
    Prev
    Next
    INDEX
    Explanations

    code structure and object instantiation

    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
    ignan
    -0.08
    eens
    -0.08
    quine
    -0.08
    ingan
    -0.08
    ÏĪη
    -0.07
    èĭ¦è¾£
    -0.07
    reh
    -0.07
    ãĥ¼ãĤ¸ãĤ§
    -0.07
    رÛĮاÙĨ
    -0.07
    èĬĿåĬł
    -0.07
    POSITIVE LOGITS
    ãĢįï¼Ī
    0.06
    odore
    0.06
    (
    0.06
     latter
    0.06
    ocha
    0.06
    бÑĥдÑĮÑĤе
    0.06
    appa
    0.06
    èĢĮéĿŀ
    0.06
    ï¼Ī
    0.06
    aight
    0.06
    Activations Density 0.032%

    No Known Activations