© 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. 11554
    Prev
    Next
    INDEX
    Explanations

    eg. examples

    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
    Ùĩ
    -0.11
    Ùħ
    -0.10
    ÙĦ
    -0.09
    ب
    -0.09
    (
    -0.09
    er
    -0.09
    h
    -0.09
    s
    -0.09
    d
    -0.08
    l
    -0.08
    POSITIVE LOGITS
    èĬ±ä¸Ģ
    0.10
    antly
    0.09
    ä¹ĭ为
    0.09
     à¹Ĩ
    0.09
    à¤ľà¥ĩ
    0.09
    ither
    0.09
    ively
    0.09
    verantwort
    0.09
    边走
    0.09
    ally
    0.08
    Activations Density 0.026%

    No Known Activations