© 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. 1732
    Prev
    Next
    INDEX
    Explanations

    say "/"

    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
    /settingsdialog
    -0.33
    åħ¨èµĦåŃIJ
    -0.31
    .IsSuccess
    -0.24
    åħ¶ä»ĸçݩ家
    -0.22
    upertino
    -0.22
     //}↵↵
    -0.21
    游æĪıå½ĵä¸Ń
    -0.21
    ---</
    -0.21
    /XMLSchema
    -0.20
    /stdc
    -0.20
    POSITIVE LOGITS
    /?
    0.28
    /#
    0.23
    #!/
    0.23
    #!
    0.23
    )new
    0.22
     trebuie
    0.21
    APON
    0.21
    /
    0.21
     âĢº
    0.20
    __.__
    0.20
    Activations Density 1.060%

    No Known Activations