© 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. 61183
    Prev
    Next
    INDEX
    Explanations

    counting occurrences, items, or records

    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
    issima
    -0.08
    ity
    -0.07
    ettings
    -0.07
    kÅĤ
    -0.07
    adero
    -0.07
    UnderTest
    -0.07
    asjons
    -0.07
    OptionsMenu
    -0.07
    æĥ³äºĨè§£æĽ´å¤ļ
    -0.07
    ovy
    -0.07
    POSITIVE LOGITS
    /count
    0.13
    =count
    0.10
     ulang
    0.09
    åĴĮåĪĨæŀIJ
    0.08
     lÆ°á»Ŀng
    0.08
    onger
    0.08
    enance
    0.08
    åĬŁå¾·
    0.08
    æľīå¤ļå°ij
    0.08
    /report
    0.08
    Activations Density 0.025%

    No Known Activations