© 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. 16552
    Prev
    Next
    INDEX
    Explanations

    bagging

    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
    ì§
    -0.07
     Aviv
    -0.07
    subset
    -0.07
    ignon
    -0.07
    mund
    -0.07
    å¤ŁäºĨ
    -0.06
     sub
    -0.06
    Ñħина
    -0.06
    äºĽ
    -0.06
    per
    -0.06
    POSITIVE LOGITS
    osu
    0.07
    aille
    0.07
    iosa
    0.07
    ENN
    0.07
    iteln
    0.07
    jera
    0.07
    quete
    0.07
    ursa
    0.07
    alai
    0.07
    ()(
    0.07
    Activations Density 0.001%

    No Known Activations