© 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. 32331
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and dates

    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
    vester
    -0.08
    еÑģÑĤи
    -0.07
    kens
    -0.07
    çĨŁæĤīäºĨ
    -0.07
    ubo
    -0.07
    PerPixel
    -0.07
    ssql
    -0.07
    éĢĴ
    -0.07
    amps
    -0.07
    aviors
    -0.07
    POSITIVE LOGITS
    olim
    0.08
    ä¸İä¼Ĺ
    0.07
    ulk
    0.07
     isNaN
    0.07
    NaN
    0.07
    -hole
    0.07
    legg
    0.07
     Hole
    0.07
    çĽĸ
    0.07
     sao
    0.07
    Activations Density 0.005%

    No Known Activations