© 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. 10679
    Prev
    Next
    INDEX
    Explanations

    `k` or `P` in mathematical contexts

    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
    sunami
    -0.07
     Plen
    -0.07
    åIJİåįĬ
    -0.06
    ÏĦÏį
    -0.06
    æĪĺç¥ŀ
    -0.06
     integra
    -0.06
    nants
    -0.06
    éĩij森
    -0.06
    å¯IJ
    -0.06
    stream
    -0.06
    POSITIVE LOGITS
    çĬ¶æĢģ
    0.08
    _strerror
    0.08
    ledo
    0.08
     estados
    0.08
     maintenance
    0.08
    StackSize
    0.07
    integer
    0.07
     Levels
    0.07
    éļİ
    0.07
     láng
    0.07
    Activations Density 0.011%

    No Known Activations