© 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. 30966
    Prev
    Next
    INDEX
    Explanations

    Free with case reference

    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
    æĭŃ
    -0.07
    çıį
    -0.07
    enth
    -0.06
    ä¸ĭåĪĹ
    -0.06
    æıŃ示
    -0.06
    ISIS
    -0.06
    ikov
    -0.06
    rim
    -0.06
    ruit
    -0.06
    éļı
    -0.06
    POSITIVE LOGITS
    uerta
    0.08
    à¹Ģà¸Ľà¸¥
    0.08
    æĹłæŃ¢å¢ĥ
    0.08
    让对æĸ¹
    0.07
    arrow
    0.07
    æ³Į
    0.07
    -issue
    0.07
    æŃ¦ä¾¯
    0.07
    ems
    0.07
    復åı¤
    0.07
    Activations Density 0.080%

    No Known Activations