© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3997
    Prev
    Next
    INDEX
    Explanations

    formal/technical context

    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
    é¾ĥ
    -0.22
    ãģªãģıãģªãģ£ãģ¦
    -0.22
    |string
    -0.21
    sı
    -0.21
    YES
    -0.21
    .Preference
    -0.21
    vais
    -0.21
    ģını
    -0.20
    .radians
    -0.20
    oriously
    -0.20
    POSITIVE LOGITS
    acades
    0.20
    _KeyDown
    0.20
    æ¹²
    0.18
    _KeyPress
    0.18
    èª
    0.18
    ÑĥÑĤ
    0.18
    漪
    0.18
    nesia
    0.17
     minHeight
    0.17
     pequeño
    0.17
    Activations Density 0.001%

    No Known Activations