© 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. 43731
    Prev
    Next
    INDEX
    Explanations

    logical order and structure

    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
    amani
    -0.09
    å¿ĥçIJĨä¸Ĭ
    -0.08
    ipa
    -0.08
    halter
    -0.08
    贷款çļĦ
    -0.08
    _DAT
    -0.08
    leger
    -0.08
    çĶŁç´ł
    -0.08
    oods
    -0.08
    æĶ¿æ²»ä¸Ĭ
    -0.08
    POSITIVE LOGITS
     sequence
    0.07
    åħĪ
    0.06
     décr
    0.06
     steps
    0.06
    顺åºı
    0.06
    éłĨçķª
    0.06
    åºı
    0.06
     progression
    0.06
     trình
    0.06
    ãģ©ãģĵãĤį
    0.06
    Activations Density 0.003%

    No Known Activations