© 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. 34041
    Prev
    Next
    INDEX
    Explanations

    special characters followed by numbers/symbols

    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
    aan
    -0.10
    macher
    -0.09
    ation
    -0.09
    esimo
    -0.09
    edio
    -0.09
    ëı
    -0.09
    esas
    -0.08
    eux
    -0.08
    ième
    -0.08
    esai
    -0.08
    POSITIVE LOGITS
    s
    0.07
    utt
    0.07
    aining
    0.07
    ships
    0.07
    ĸ
    0.07
    ÑĢай
    0.07
    heels
    0.07
    Ùħا
    0.06
    nya
    0.06
    side
    0.06
    Activations Density 0.017%

    No Known Activations