© 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. 18446
    Prev
    Next
    INDEX
    Explanations

    rental synchronization

    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
    åĢŁåĬĽ
    -0.08
    éĴĪ对æĢ§
    -0.08
    æłij人
    -0.07
    亿人
    -0.07
    ocop
    -0.07
    çĸ¾
    -0.07
     Kanz
    -0.07
     Mej
    -0.07
    ENDING
    -0.07
    为æ°ij
    -0.07
    POSITIVE LOGITS
    ä¸įæŃ»
    0.07
    hão
    0.07
     royalty
    0.07
    Markup
    0.07
     profits
    0.07
    esis
    0.07
     appropriated
    0.06
    åĪĨéħįçļĦ
    0.06
     managerial
    0.06
    æºĸ
    0.06
    Activations Density 0.003%

    No Known Activations