© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1693
    Prev
    Next
    INDEX
    Explanations

    names and specific entities

    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
    讵
    -0.21
    ichi
    -0.20
    #ga
    -0.20
    ðŁ¤ĵ
    -0.19
    upplier
    -0.19
    /null
    -0.19
    æĦĨ
    -0.19
    ItemSelectedListener
    -0.19
    åĻ¼
    -0.19
    (strpos
    -0.18
    POSITIVE LOGITS
    bower
    0.20
    .Basic
    0.20
    .getWriter
    0.19
    eah
    0.19
    prise
    0.18
    hasOne
    0.18
    VERN
    0.18
    rut
    0.18
    'utilisation
    0.17
    cej
    0.17
    Activations Density 0.001%

    No Known Activations