© 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. 22389
    Prev
    Next
    INDEX
    Explanations

    sample size $n$

    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
    ueux
    -0.09
    âu
    -0.08
    eshire
    -0.08
    alow
    -0.07
     Alc
    -0.07
    classes
    -0.07
    ilin
    -0.07
     Gusta
    -0.07
    à¸IJ
    -0.07
    chten
    -0.07
    POSITIVE LOGITS
    ç»Łè®¡åѦ
    0.07
    ANO
    0.07
     numeros
    0.07
    æł·æľ¬
    0.07
     samples
    0.07
    ç»Łè®¡
    0.07
    çĬ¯
    0.07
    çļĦèIJ¥åħ»
    0.06
    /bootstrap
    0.06
    æĭ¼
    0.06
    Activations Density 0.008%

    No Known Activations