© 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. 23141
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and variable declarations

    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
    ier
    -0.07
    zim
    -0.06
    iern
    -0.06
    iers
    -0.06
    æľīæĸĻ
    -0.06
    æĸ¹åIJijåıijå±ķ
    -0.06
    ould
    -0.06
    atcher
    -0.06
    ç£Ĭ
    -0.06
    erte
    -0.06
    POSITIVE LOGITS
    heit
    0.09
    atismo
    0.08
    ablo
    0.07
    astian
    0.07
    жÑĮ
    0.07
    _DEFINED
    0.07
    OOT
    0.07
    åľ°ä¹ħ
    0.07
    vided
    0.07
     rằng
    0.07
    Activations Density 0.002%

    No Known Activations