© 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. 51654
    Prev
    Next
    INDEX
    Explanations

    cars daily, theorem says

    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
    å±¥è¡Į
    -0.07
    çī¹å°Ķ
    -0.07
    ilige
    -0.07
    ngth
    -0.07
    antai
    -0.07
    åİŁä»·
    -0.07
     Tel
    -0.07
    Tel
    -0.07
    COPE
    -0.07
    æ±ĤçĶŁ
    -0.07
    POSITIVE LOGITS
    èĻ
    0.08
     dụ
    0.07
    verkehr
    0.07
    ê¼
    0.06
    vis
    0.06
    odor
    0.06
    medi
    0.06
     marching
    0.06
    (inter
    0.06
    à¹Ĥà¸ļ
    0.06
    Activations Density 0.001%

    No Known Activations