© 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. 62397
    Prev
    Next
    INDEX
    Explanations

    one class

    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
    ä¸Ģ个个
    -0.12
     ones
    -0.10
     themselves
    -0.10
    èĢħ们
    -0.10
    venes
    -0.09
    æĸ°ä¸Ģè½®
    -0.09
    éĥ½æĺ¯ä¸ĢäºĽ
    -0.09
    illions
    -0.09
    ä¸Ģéģĵéģĵ
    -0.08
    çļĦä¸ĢäºĽ
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.14
    ìĶ©
    0.13
    åĴĮä¸Ģ个
    0.11
    ãģļãģ¤
    0.11
    andone
    0.10
    æĪĸå°ij
    0.09
    æĪĸå¤ļ
    0.09
    å°±å¤ŁäºĨ
    0.08
     duy
    0.08
     sequer
    0.08
    Activations Density 0.219%

    No Known Activations