© 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. 45746
    Prev
    Next
    INDEX
    Explanations

    parentheses around numbers

    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
    ppo
    -0.07
    ing
    -0.06
    å®ľ
    -0.06
    å¿Į
    -0.06
    agar
    -0.06
    æ®ĭ
    -0.06
    ׳×ĺ
    -0.06
    åħ·
    -0.06
    éĢł
    -0.06
    ake
    -0.06
    POSITIVE LOGITS
    istrik
    0.08
    åĪ©çī©
    0.08
    -caret
    0.08
    Subview
    0.08
    arel
    0.07
    idth
    0.07
     mesti
    0.07
    utas
    0.07
    oader
    0.07
    leneck
    0.07
    Activations Density 0.001%

    No Known Activations