© 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. 33716
    Prev
    Next
    INDEX
    Explanations

    gene regions and loci

    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
    åŁºæķ°
    -0.07
    à¸ķัà¹īà¸ĩ
    -0.06
    urers
    -0.06
    ifax
    -0.06
    åĬłåİĭ
    -0.06
     Keg
    -0.06
    ignon
    -0.06
    urer
    -0.06
    áīµ
    -0.06
    æŃ£è§Ĩ
    -0.06
    POSITIVE LOGITS
    -marker
    0.09
    åĮºåŁŁåĨħçļĦ
    0.09
     regions
    0.09
     tract
    0.09
    oola
    0.08
     sweeps
    0.08
    ebak
    0.08
     ÑĥÑĩаÑģÑĤки
    0.08
     swath
    0.08
     parcel
    0.08
    Activations Density 0.027%

    No Known Activations