© 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. 3268
    Prev
    Next
    INDEX
    Explanations

    specific entities or topics

    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
    icerca
    -0.23
    afort
    -0.21
     prosecuting
    -0.20
    æ¿¡
    -0.20
    atever
    -0.20
    ERVICE
    -0.19
    vest
    -0.19
    ACHINE
    -0.19
    -labelled
    -0.18
    _strlen
    -0.18
    POSITIVE LOGITS
    Türkiye
    0.24
    ómo
    0.22
    zelf
    0.22
    -Methods
    0.21
     <",
    0.21
    ".↵↵↵↵
    0.21
    rigesimal
    0.21
     avalia
    0.20
    âĦħ
    0.20
    olon
    0.20
    Activations Density 0.001%

    No Known Activations