© 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. 408
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    aeda
    -0.31
    (strpos
    -0.30
    akest
    -0.27
    chestra
    -0.26
    ãģĻãģĵãģ¨
    -0.24
    iage
    -0.23
    ecycle
    -0.23
    akter
    -0.23
    éĢħ
    -0.23
    âĺħâĺħ
    -0.23
    POSITIVE LOGITS
    à¹Į
    0.37
    Ø©
    0.32
    ies
    0.30
    ium
    0.30
    able
    0.29
    æį¢åı¥è¯Ŀ
    0.29
    ie
    0.29
    ia
    0.27
    Ùī
    0.27
    ica
    0.27
    Activations Density 5.420%

    No Known Activations