© 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. 27559
    Prev
    Next
    INDEX
    Explanations

    active visit

    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
    éĹ´çļĦ
    -0.08
    PLY
    -0.07
    ubar
    -0.07
    並
    -0.07
    UPER
    -0.07
    ':"
    -0.06
    inosaur
    -0.06
    ãĥłãģ®
    -0.06
    anson
    -0.06
     Seger
    -0.06
    POSITIVE LOGITS
    æĵİ
    0.07
    .true
    0.07
    ansch
    0.07
    uky
    0.07
    zyman
    0.06
    EXPECTED
    0.06
     rocked
    0.06
    .interfaces
    0.06
    åĬª
    0.06
     Assass
    0.06
    Activations Density 0.011%

    No Known Activations