© 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. 26795
    Prev
    Next
    INDEX
    Explanations

    hexadecimal escape sequences

    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
    åİŁçĶŁ
    -0.08
    gress
    -0.07
    stream
    -0.07
    ÅŁa
    -0.07
    ylon
    -0.07
    ulls
    -0.07
    _both
    -0.07
    ulan
    -0.07
    èĢĮæĿ¥çļĦ
    -0.07
    éªĭ
    -0.07
    POSITIVE LOGITS
    OF
    0.07
    obot
    0.07
    amat
    0.07
    agnes
    0.07
    hof
    0.07
    vat
    0.07
    ippo
    0.06
    iba
    0.06
    èĵĦçĶµæ±ł
    0.06
    IPP
    0.06
    Activations Density 0.021%

    No Known Activations