© 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. 45605
    Prev
    Next
    INDEX
    Explanations

    numbers with č

    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
    èݱ德
    -0.08
    جÙĦØ©
    -0.07
    koch
    -0.07
    æ¾İ
    -0.07
    aro
    -0.07
    plib
    -0.07
    å¦Ĥæ½®
    -0.07
    å±ķå¼ĢäºĨ
    -0.07
     overlays
    -0.07
    likelihood
    -0.07
    POSITIVE LOGITS
     Yar
    0.06
    æķ´
    0.06
    afa
    0.06
    åī©
    0.06
    à¹Ĥย
    0.06
    lein
    0.06
    产æĿĥæĪ¿
    0.06
    eth
    0.06
     comp
    0.06
    _representation
    0.06
    Activations Density 0.182%

    No Known Activations