© 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. 43154
    Prev
    Next
    INDEX
    Explanations

    directions, changes, states

    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
    iesto
    -0.08
    oug
    -0.08
    ONGO
    -0.08
    åĴĮçĪ±
    -0.08
    ableView
    -0.08
    party
    -0.07
    ÑĢÑĥÑĤ
    -0.07
    izzo
    -0.07
    oha
    -0.07
    <[
    -0.07
    POSITIVE LOGITS
    个ä¸ĵä¸ļ
    0.07
     Amat
    0.07
    亦çĦ¶
    0.06
    ׳×Ĵ
    0.06
    ç¡
    0.06
    ä¹ŁåIJĮæł·
    0.06
    xing
    0.06
    çŃīåħ¶ä»ĸ
    0.06
    cik
    0.06
    æĨ
    0.06
    Activations Density 0.022%

    No Known Activations