© 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. 1678
    Prev
    Next
    INDEX
    Explanations

    story elements

    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
     libertine
    -0.37
     unmist
    -0.33
     sodom
    -0.32
     Escorts
    -0.31
     fierc
    -0.31
     erotica
    -0.29
     orgy
    -0.29
    çĹ¼
    -0.29
     murderers
    -0.27
     sophistic
    -0.27
    POSITIVE LOGITS
     lowes
    0.28
    ç¾İåªĴ
    0.27
     plot
    0.25
    âĦł
    0.25
    为主线
    0.24
    åķIJ
    0.24
    åĩºåľº
    0.24
    :disable
    0.23
    å¿ĥ仪çļĦ
    0.23
     WIFI
    0.23
    Activations Density 2.684%

    No Known Activations