© 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. 62129
    Prev
    Next
    INDEX
    Explanations

    INTERNAL REVENUE, Investigation, kitchen

    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
    uyer
    -0.08
    èĵī
    -0.07
    ç¢į
    -0.07
    ymp
    -0.07
    å°Ķå¾·
    -0.07
    .Sequence
    -0.07
    éĩį温
    -0.07
    еле
    -0.06
    .LayoutParams
    -0.06
    aldo
    -0.06
    POSITIVE LOGITS
    stro
    0.07
    issi
    0.06
    æīĢåIJij
    0.06
    _ACL
    0.06
    ouflage
    0.06
    æľīè¿Ļä¹Ī
    0.06
    är
    0.06
    artin
    0.06
    opol
    0.06
    ç»ıæµİ管çIJĨ
    0.06
    Activations Density 0.040%

    No Known Activations