© 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. 13891
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming concepts

    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
    arial
    -0.07
    çķĮ
    -0.06
    ara
    -0.06
    æŶæ¯ı
    -0.06
    æŀĹçĭ¬
    -0.06
    çīµ
    -0.06
    imity
    -0.06
    andang
    -0.06
    çķĮçļĦ
    -0.06
    minster
    -0.06
    POSITIVE LOGITS
    annes
    0.08
    kep
    0.08
    ioms
    0.07
    iates
    0.07
    zion
    0.07
    TES
    0.07
    anel
    0.07
    lettes
    0.07
    vider
    0.07
    ahlen
    0.07
    Activations Density 0.608%

    No Known Activations