© 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. 55509
    Prev
    Next
    INDEX
    Explanations

    list delimiters and closing symbols

    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
    aimana
    -0.08
    arella
    -0.08
    arden
    -0.07
    oren
    -0.07
    æĴĩ
    -0.07
    ertest
    -0.07
    isset
    -0.07
    uding
    -0.07
    Dettagli
    -0.07
    ç½ij游ä¹ĭ
    -0.07
    POSITIVE LOGITS
    laud
    0.07
    ÛĮÙģ
    0.07
    lü
    0.07
    ROP
    0.07
    etet
    0.07
    (strict
    0.06
    èĤĩ
    0.06
    Ĥ
    0.06
    ondi
    0.06
    onse
    0.06
    Activations Density 0.026%

    No Known Activations