© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1236
    Prev
    Next
    INDEX
    Explanations

    Legal case citations

    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
    ":"'
    -0.24
     blackColor
    -0.23
     whiteColor
    -0.23
    même
    -0.22
     clearColor
    -0.20
    thora
    -0.19
    Chicken
    -0.19
     lack
    -0.19
     zun
    -0.18
    ç¡Į
    -0.18
    POSITIVE LOGITS
    aeda
    0.26
    çݩ家æľĭåıĭ
    0.26
    ilmington
    0.25
    åĪ©çĶ¨æĤ¨çļĦ
    0.24
    styleType
    0.23
     actionTypes
    0.22
    swire
    0.22
    游æĪıæĬĢå·§
    0.22
    @dynamic
    0.21
    imson
    0.21
    Activations Density 0.268%

    No Known Activations