© 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. 1288
    Prev
    Next
    INDEX
    Explanations

    actions/behavior

    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
     incarcer
    -0.31
     erotica
    -0.28
    RenderTarget
    -0.24
     sodom
    -0.23
    -animation
    -0.23
     PIXEL
    -0.23
    对åħ¶çľŁå®ŀ
    -0.23
     bigot
    -0.22
     intox
    -0.22
    PixelFormat
    -0.22
    POSITIVE LOGITS
    è¡Į为
    0.32
    è¿Ŀåıį
    0.29
    è¡ĮçĤº
    0.28
     behavior
    0.27
    æĥħèĬĤ
    0.26
    çļĦè¡Į为
    0.26
     behaviors
    0.26
     acts
    0.26
     actions
    0.25
    è¿Ŀæ³ķè¡Į为
    0.25
    Activations Density 2.363%

    No Known Activations