© 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. 51514
    Prev
    Next
    INDEX
    Explanations

    numbers and "field"

    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
    hem
    -0.07
     ÐŃкономи
    -0.07
    ere
    -0.07
    å®ŀå±ŀ
    -0.06
    igh
    -0.06
    sequent
    -0.06
    åªĴ
    -0.06
     Kese
    -0.06
    ady
    -0.06
    羣å¿ĥçļĦ
    -0.06
    POSITIVE LOGITS
    Ú¯ÙĪ
    0.08
    άÏĤ
    0.07
    继ç»Ńä¿ĿæĮģ
    0.07
    ettino
    0.07
    JA
    0.07
    bert
    0.07
    itim
    0.07
    åĨį继ç»Ń
    0.07
    éĺħ
    0.07
    åı£æ°Ķ
    0.07
    Activations Density 0.001%

    No Known Activations