© 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. 919
    Prev
    Next
    INDEX
    Explanations

    Stack related errors or communities

    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
    ä¸įåĨ³
    -0.10
     busty
    -0.10
    eeee
    -0.09
    à§įস
    -0.09
     dÃłng
    -0.09
    Ø·ÙĦÙĤت
    -0.09
    veau
    -0.09
    icona
    -0.09
    tingham
    -0.08
    rippling
    -0.08
    POSITIVE LOGITS
    ingly
    0.10
    pile
    0.09
    iness
    0.09
    ness
    0.08
    mates
    0.08
    mate
    0.08
    جة
    0.07
    ed
    0.07
    busters
    0.07
    p
    0.07
    Activations Density 0.075%

    No Known Activations