© 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. 26651
    Prev
    Next
    INDEX
    Explanations

    give x

    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
    versa
    -0.09
    garan
    -0.08
    renom
    -0.08
    ushman
    -0.07
    åľĪ
    -0.07
    _lengths
    -0.07
    brands
    -0.07
    anze
    -0.07
    apiro
    -0.07
     vét
    -0.07
    POSITIVE LOGITS
    uhl
    0.07
    åħ¬å¼ĢæĭĽèģĺ
    0.06
     ê³Ħ
    0.06
     ten
    0.06
     Germ
    0.06
    zy
    0.06
    桶
    0.06
    åį³æĹ¥
    0.06
    ãĤ³ãĥ¼
    0.06
    åħ¬åı·
    0.06
    Activations Density 0.001%

    No Known Activations