© 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. 29844
    Prev
    Next
    INDEX
    Explanations

    no

    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
    æľīæŶ
    -0.07
    ohn
    -0.06
     sometimes
    -0.06
    æ£ł
    -0.06
     Cul
    -0.06
    æľīæŶåĢĻ
    -0.06
     Jac
    -0.06
    容
    -0.06
     triple
    -0.06
    vic
    -0.06
    POSITIVE LOGITS
    unless
    0.10
    æijĩ头
    0.10
    éĻ¨
    0.10
     Unless
    0.09
     unless
    0.09
    éĻ¤éĿŀ
    0.09
    éĢļéĢļ
    0.09
    abee
    0.08
    æijĩäºĨæijĩ头
    0.08
     ÑĢазве
    0.08
    Activations Density 0.115%

    No Known Activations