© 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. 34042
    Prev
    Next
    INDEX
    Explanations

    mathematical analysis and theory

    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
    opter
    -0.08
    akwa
    -0.08
    kea
    -0.07
    伶
    -0.07
    åĢĴéľī
    -0.07
    åĩ«
    -0.07
    portun
    -0.07
    riott
    -0.07
    æĭīå°Ķ
    -0.07
    ismet
    -0.07
    POSITIVE LOGITS
    级
    0.07
    ilu
    0.07
     tensor
    0.07
    anton
    0.07
    æī±
    0.07
    éĺ¶
    0.07
    常客
    0.07
    级çļĦ
    0.07
     Pug
    0.06
     sme
    0.06
    Activations Density 0.001%

    No Known Activations