© 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. 56007
    Prev
    Next
    INDEX
    Explanations

    key with value

    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
    iamo
    -0.07
    uan
    -0.07
    æĬľ
    -0.06
    igma
    -0.06
     íĽĦë³´
    -0.06
     Ber
    -0.06
    ise
    -0.06
    çľº
    -0.06
    éĹ»è¨Ģ
    -0.06
    Ø«ÙĨ
    -0.06
    POSITIVE LOGITS
     named
    0.10
    åIJį为
    0.09
    åIJįçĤº
    0.08
    åIJį
    0.07
    daf
    0.07
    ihan
    0.07
    åIJį称
    0.07
    inkan
    0.07
    -name
    0.07
    νομ
    0.07
    Activations Density 0.017%

    No Known Activations