© 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. 26056
    Prev
    Next
    INDEX
    Explanations

    shapes like circular or rectangular

    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
    izza
    -0.08
    ørt
    -0.08
    izzer
    -0.07
    lessly
    -0.07
    izzo
    -0.07
    ieties
    -0.07
    lessness
    -0.07
    less
    -0.07
    ãĤªãĥªãĥ³
    -0.07
    umpa
    -0.07
    POSITIVE LOGITS
    -shaped
    0.11
    å½¢çļĦ
    0.09
    кеÑĤ
    0.08
    å½¢èī²
    0.07
    -headed
    0.07
    /apple
    0.07
    å½¢çĬ¶çļĦ
    0.07
    jad
    0.06
    -ish
    0.06
    terr
    0.06
    Activations Density 0.025%

    No Known Activations