© 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. 51756
    Prev
    Next
    INDEX
    Explanations

    comment markers

    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
    ieri
    -0.08
    occo
    -0.08
    .jquery
    -0.08
    æĺ¥æĿ¥
    -0.08
    æĹłäºĭ
    -0.08
    çļĦå°±
    -0.08
    aje
    -0.08
    irmi
    -0.07
    iale
    -0.07
    mend
    -0.07
    POSITIVE LOGITS
    ssf
    0.06
    å¹
    0.06
    orest
    0.06
    0.06
    ç¿
    0.06
    ÑĦаÑĢ
    0.06
    rete
    0.05
    Ŀ
    0.05
    å¿ĹåĪļ
    0.05
    é©°
    0.05
    Activations Density 0.166%

    No Known Activations