© 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. 50514
    Prev
    Next
    INDEX
    Explanations

    fish oil

    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
    ter
    -0.08
    çī©è³ĩ
    -0.08
    पà¥Ĥरà¥įण
    -0.08
    ëĮĢë¡ľ
    -0.08
    ìĤ¬íķŃ
    -0.08
    gers
    -0.08
    istar
    -0.07
    ighton
    -0.07
    éĩijæĸ¯
    -0.07
    oriously
    -0.07
    POSITIVE LOGITS
    erman
    0.09
    İ
    0.08
    ermen
    0.08
    ying
    0.07
    adelphia
    0.07
    ify
    0.07
    hood
    0.07
    ĸ
    0.07
    nap
    0.07
    -eye
    0.07
    Activations Density 0.025%

    No Known Activations