© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32951
    Prev
    Next
    INDEX
    Explanations

    conditional logic structures

    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
    cito
    -0.08
    orr
    -0.07
    æĵħ
    -0.07
     kolej
    -0.07
    кола
    -0.07
    .inject
    -0.07
    á»Į
    -0.07
     lÃłnh
    -0.07
    éħ¸çĶľèĭ¦è¾£
    -0.07
    zyn
    -0.07
    POSITIVE LOGITS
     otherwise
    0.13
     Otherwise
    0.12
    otherwise
    0.11
    Otherwise
    0.11
     ê·¸ëłĩì§Ģ
    0.10
    åIJ¦åĪĻ
    0.10
    åIJ¦åīĩ
    0.09
     инаÑĩе
    0.09
     else
    0.08
    ä¸įçĦ¶
    0.08
    Activations Density 0.061%

    No Known Activations