© 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. 20002
    Prev
    Next
    INDEX
    Explanations

    code repository identifiers

    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
    ain
    -0.07
    ono
    -0.07
    两个æĸ¹éĿ¢
    -0.06
    rett
    -0.06
    adol
    -0.06
    çī¹åĪ«æĺ¯
    -0.06
    çī¹åĪ«æĺ¯åľ¨
    -0.06
    ende
    -0.06
    æµĴ
    -0.06
    aint
    -0.06
    POSITIVE LOGITS
    åĴĮ第äºĮ
    0.08
    å¾Ĺå¿ĥ
    0.08
    <|repo_name|>
    0.07
    çľĭä¸į
    0.07
    inel
    0.07
    æīĵå®Į
    0.07
    æĿ¥ä¸ª
    0.07
    Ù°
    0.07
    ì·¨
    0.07
    æĪĸå¤ļ个
    0.07
    Activations Density 0.047%

    No Known Activations