© 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. 49106
    Prev
    Next
    INDEX
    Explanations

    JSON processing libraries/tools

    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
    ä½Ĩ并ä¸į
    -0.08
    erecht
    -0.08
    uster
    -0.07
    ä½ĨåIJĮæŶ
    -0.06
    scribe
    -0.06
    chal
    -0.06
     right
    -0.06
    rawer
    -0.06
    feit
    -0.06
    æķ´æķ´
    -0.06
    POSITIVE LOGITS
    åĪĻæĺ¯
    0.11
     likewise
    0.10
    亦çĦ¶
    0.10
     tampoco
    0.10
    åĪĻä¼ļ
    0.09
     wiederum
    0.09
    åīĩæĺ¯
    0.09
     enfin
    0.09
    æĽ´ä¸įä¼ļ
    0.09
    åĪĻéľĢè¦ģ
    0.09
    Activations Density 0.010%

    No Known Activations