© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3017
    Prev
    Next
    INDEX
    Explanations

    communication systems

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æıĨ
    -0.25
    ä¸ī大éĺ¶æ®µ
    -0.25
    ãİĿ
    -0.23
    ,'#
    -0.22
    ãİŀ
    -0.22
    æĽ·
    -0.22
    eya
    -0.22
    иÑĩеÑģ
    -0.21
    'options
    -0.20
    -Version
    -0.20
    POSITIVE LOGITS
    lee
    0.21
     Presidency
    0.21
     layoutParams
    0.20
    oÃłi
    0.20
    stdafx
    0.19
     interracial
    0.19
    æķ£
    0.19
     skeletal
    0.19
     ownerId
    0.18
    Feat
    0.18
    Activations Density 0.002%

    No Known Activations