© 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. 11213
    Prev
    Next
    INDEX
    Explanations

    subsequence or substring matching

    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
    utoff
    -0.08
    radius
    -0.07
     Radius
    -0.07
    à¹īาว
    -0.07
    arrant
    -0.07
    éĿĴäºij
    -0.07
     Perry
    -0.07
    ictured
    -0.07
    .Locale
    -0.07
    æĸ¹åľĨ
    -0.07
    POSITIVE LOGITS
    sequence
    0.09
    seq
    0.09
     seq
    0.08
    åºıåĪĹ
    0.08
    æŶåºı
    0.08
    éch
    0.08
     sequences
    0.08
     sequence
    0.07
    uco
    0.07
     subsequ
    0.07
    Activations Density 0.004%

    No Known Activations