© 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. 38991
    Prev
    Next
    INDEX
    Explanations

    ãĢĤ

    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
    ãĥ³
    -0.08
    althy
    -0.08
    ozilla
    -0.08
    ../../../
    -0.07
    ìĦľ
    -0.07
    earch
    -0.07
    aum
    -0.07
     lévÅij
    -0.07
    iates
    -0.07
    urre
    -0.07
    POSITIVE LOGITS
    nen
    0.10
    ĥ
    0.09
    nya
    0.09
    utta
    0.09
    تÙĬÙĨ
    0.09
    innen
    0.08
    ture
    0.08
    تاÙĨ
    0.08
    nak
    0.08
    rive
    0.08
    Activations Density 0.024%

    No Known Activations