© 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. 2309
    Prev
    Next
    INDEX
    Explanations

    strange characters

    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
     rencontrer
    -0.21
    _inds
    -0.21
     "','
    -0.21
    aload
    -0.20
    @store
    -0.20
    -pill
    -0.20
    à¸Ĵ
    -0.19
    âģİ
    -0.19
    inel
    -0.19
    Precision
    -0.18
    POSITIVE LOGITS
     Escorts
    0.23
    æİĩ
    0.23
    游æĪıæĬĢå·§
    0.22
    ãĥµ
    0.22
     ÐŁÐ¾Ñĩем
    0.22
    são
    0.21
     Escort
    0.21
    ãģįãĤĮ
    0.21
    éĵ©
    0.21
    èĪ¾
    0.21
    Activations Density 0.001%

    No Known Activations