© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32914
    Prev
    Next
    INDEX
    Explanations

    code block terminators

    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
    åįģæĿ¡
    -0.07
    æĶ
    -0.07
    adh
    -0.07
    rof
    -0.06
    usc
    -0.06
    稼
    -0.06
    ÐĴÐĶ
    -0.06
     benchmark
    -0.06
    ungan
    -0.06
     gent
    -0.06
    POSITIVE LOGITS
    è¿ijè·Ŀ离
    0.08
    æĸŃç»Ń
    0.07
     exac
    0.07
    attet
    0.07
    annis
    0.07
    æķ¬
    0.07
    gab
    0.07
    osomal
    0.07
    rin
    0.07
    номо
    0.07
    Activations Density 0.004%

    No Known Activations