© 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. 57636
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
    elv
    -0.08
    lyph
    -0.08
    unis
    -0.08
    åį§é¾Ļ
    -0.08
    лко
    -0.08
    æķĻèĤ²ä¸Ńå¿ĥ
    -0.08
    ä½łè¿Ļæĺ¯
    -0.08
    çĻ¾äºº
    -0.08
    schau
    -0.07
     lho
    -0.07
    POSITIVE LOGITS
    ider
    0.08
    uvi
    0.07
    ç´§ç´§åľ°
    0.07
    åıĹåĪ°äºĨ
    0.06
    mailer
    0.06
    缴æݥ就
    0.06
    æľīåĩł
    0.06
    mile
    0.06
    ç§
    0.06
    ati
    0.06
    Activations Density 0.254%

    No Known Activations