© 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. 3058
    Prev
    Next
    INDEX
    Explanations

    inin ain this

    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
    Statics
    -0.07
    гани
    -0.06
    lesias
    -0.06
    loating
    -0.06
    绩
    -0.06
    -pre
    -0.06
    rades
    -0.06
    инима
    -0.06
    ongoose
    -0.06
    Wide
    -0.06
    POSITIVE LOGITS
    lio
    0.09
    请注æĺİ
    0.07
    iox
    0.07
    åIJ«
    0.07
    endra
    0.07
    li
    0.07
    è¯·çĽ´æİ¥
    0.06
    nei
    0.06
    вий
    0.06
    lÃŃ
    0.06
    Activations Density 0.029%

    No Known Activations