© 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. 48651
    Prev
    Next
    INDEX
    Explanations

    names and lists

    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
    heim
    -0.07
    ReturnType
    -0.07
     akin
    -0.07
    她è¿ĺ
    -0.07
    /close
    -0.07
     ill
    -0.06
    çİ°æĪ¿
    -0.06
    vf
    -0.06
    upi
    -0.06
    æѤ类
    -0.06
    POSITIVE LOGITS
    IBIL
    0.07
    ानà¥Ģ
    0.07
    ãĥĦãĥł
    0.07
    inov
    0.07
     alone
    0.07
    ogs
    0.07
    æľ¬èº«
    0.07
    ans
    0.07
    ä»ħæľīçļĦ
    0.07
    кÑĢа
    0.07
    Activations Density 0.023%

    No Known Activations