© 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. 49015
    Prev
    Next
    INDEX
    Explanations

    without going into

    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
    aug
    -0.08
    ارة
    -0.08
    æĢªä¸įå¾Ĺ
    -0.08
    bes
    -0.08
    ynos
    -0.07
    usto
    -0.07
    bett
    -0.07
    uck
    -0.07
    ummy
    -0.07
    nyder
    -0.07
    POSITIVE LOGITS
     specifics
    0.11
     details
    0.11
    ç»ĨèĬĤ
    0.10
    åħ·ä½ĵçļĦ
    0.10
    รายละà¹Ģà¸Ńียà¸Ķ
    0.09
     detail
    0.09
    åħ·ä½ĵåĨħ容
    0.09
     détails
    0.09
     detailed
    0.09
     Details
    0.09
    Activations Density 0.011%

    No Known Activations