© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27243
    Prev
    Next
    INDEX
    Explanations

    starting text of a list

    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
    çľ¼çľ¶
    -0.07
     %-
    -0.06
    ODY
    -0.06
    igy
    -0.06
     too
    -0.06
    åįıä¼ļ
    -0.06
    ToAdd
    -0.06
    éĤ£ä¸į
    -0.06
    æĬĺä¼ĺæĥł
    -0.06
     depth
    -0.06
    POSITIVE LOGITS
    egger
    0.08
    اÙħÙĨ
    0.08
    iders
    0.08
    kke
    0.07
    éĿĴéĿĴ
    0.07
    elsey
    0.07
    温
    0.07
    елей
    0.07
    ancock
    0.07
    润åıij
    0.07
    Activations Density 0.041%

    No Known Activations