© 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. 26715
    Prev
    Next
    INDEX
    Explanations

    academic titles and citations

    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
     Gang
    -0.07
    ip
    -0.07
    il
    -0.06
    绣
    -0.06
    iz
    -0.06
    agh
    -0.06
    it
    -0.06
    ç«ĭåį³ä¸ĭè½½
    -0.06
    âĢ¦
    -0.06
    Âł
    -0.06
    POSITIVE LOGITS
    alian
    0.09
    номо
    0.08
    ĥģ
    0.08
    ocks
    0.08
    ĥĿ
    0.08
    ujur
    0.08
    uris
    0.08
    alus
    0.08
    ermann
    0.07
    retti
    0.07
    Activations Density 0.015%

    No Known Activations