© 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. 12600
    Prev
    Next
    INDEX
    Explanations

    737 max jets

    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
    inia
    -0.08
    æ¸į
    -0.06
    åĮħ车
    -0.06
    rules
    -0.06
    èµĽåĮº
    -0.06
    æıIJåıĸ
    -0.06
    åŀ¢
    -0.06
    éªĩ
    -0.06
    mess
    -0.06
    omez
    -0.06
    POSITIVE LOGITS
    ç³»åĪĹçļĦ
    0.08
    æĺİä¿¡
    0.08
    neo
    0.08
    edos
    0.07
    åŃĹåŀĭ
    0.07
    姨
    0.07
    eload
    0.07
    enne
    0.07
    çĨŁç»ĥ
    0.07
    å©¿
    0.07
    Activations Density 0.082%

    No Known Activations