© 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. 26328
    Prev
    Next
    INDEX
    Explanations

    numbers followed by time indicators

    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
    hood
    -0.08
    éĻħ
    -0.08
    asley
    -0.08
    ToLocal
    -0.08
    sembled
    -0.07
    rij
    -0.07
    omar
    -0.07
    ừng
    -0.07
    éļĽ
    -0.07
     pháºŃn
    -0.07
    POSITIVE LOGITS
    esima
    0.09
    Carthy
    0.08
    gether
    0.08
    opolitan
    0.08
    ongodb
    0.07
    esimo
    0.07
    аÑģÑģив
    0.07
    eppe
    0.07
    ening
    0.07
    inke
    0.07
    Activations Density 0.236%

    No Known Activations