© 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. 21015
    Prev
    Next
    INDEX
    Explanations

    1

    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
    åĬ¨åĬĽ
    -0.07
    ahari
    -0.07
    inos
    -0.07
    erland
    -0.07
    ectomy
    -0.06
    åijĺ
    -0.06
    avian
    -0.06
    èIJĥåıĸ
    -0.06
    ç²ī
    -0.06
     Vest
    -0.06
    POSITIVE LOGITS
    ηÏĥη
    0.07
    æĦıæ°Ķ
    0.07
    å°ıçľĭ
    0.07
    otel
    0.07
    æŃ¤èµ·
    0.07
    åħĪåĪ°
    0.07
    ighth
    0.07
    .hom
    0.06
    ichen
    0.06
    æĽ
    0.06
    Activations Density 0.004%

    No Known Activations