© 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. 30913
    Prev
    Next
    INDEX
    Explanations

    epithelial cells, mouth, cats, fun

    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
    ami
    -0.07
    luss
    -0.07
    lian
    -0.06
    æ¾³
    -0.06
    庸
    -0.06
    æŀģ
    -0.06
    ract
    -0.06
    èµĦ
    -0.06
     tast
    -0.06
    urf
    -0.06
    POSITIVE LOGITS
    untime
    0.08
     SWAT
    0.08
    wik
    0.07
    WithValue
    0.07
    ritable
    0.07
    -git
    0.07
    åĴĮçĶŁäº§
    0.07
    两æĪ¿
    0.07
    ikip
    0.07
    åĽŀå¸ĸ
    0.07
    Activations Density 0.841%

    No Known Activations