© 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. 27447
    Prev
    Next
    INDEX
    Explanations

    program, process, syndrome, scandal, race

    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
    对äºİè¿ĻäºĽ
    -0.07
    umped
    -0.07
    èİħ
    -0.07
     exhibiting
    -0.07
    éļ¾åħį
    -0.06
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.06
    å°±æĦıåij³çĿĢ
    -0.06
    ienes
    -0.06
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    -0.06
    lotte
    -0.06
    POSITIVE LOGITS
    åıĪåı«
    0.12
    åıĪ称
    0.12
    åıĪåIJį
    0.12
    ä¹Łåı«
    0.11
    åıĪ称为
    0.11
    è¿Ļæĺ¯ä¸Ģç§į
    0.11
    å®ĥæĺ¯ä¸Ģç§į
    0.10
    ä¹Łè¢«ç§°ä¸º
    0.10
    æĺ¯ä¸Ģç§į
    0.10
    ä¹Łç§°
    0.10
    Activations Density 0.478%

    No Known Activations