© 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. 3690
    Prev
    Next
    INDEX
    Explanations

    Because of

    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
    egrator
    -0.26
     WHETHER
    -0.23
    ût
    -0.21
    {{--
    -0.21
    åĽłç´ł
    -0.19
     اÙĦسابع
    -0.19
    ç½ijé¦ĸ页
    -0.19
    æѸ
    -0.19
    ws
    -0.19
    -0.19
    POSITIVE LOGITS
    osemite
    0.25
    omination
    0.24
     its
    0.24
    upakan
    0.21
    undra
    0.20
     FlatButton
    0.20
    ConfigurationException
    0.20
    rippling
    0.20
    umbnail
    0.19
    icans
    0.19
    Activations Density 0.112%

    No Known Activations