© 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. 1910
    Prev
    Next
    INDEX
    Explanations

    When

    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
    1
    -0.42
    3
    -0.40
    2
    -0.40
    4
    -0.39
    5
    -0.37
    0
    -0.36
    6
    -0.35
    9
    -0.34
    8
    -0.33
    7
    -0.32
    POSITIVE LOGITS
    __;
    0.46
    ******↵↵
    0.42
    *****↵↵
    0.41
    -With
    0.40
    /MPL
    0.40
    /if
    0.39
    :;↵
    0.38
    DMI
    0.38
    âĵĴ
    0.37
    ___↵↵
    0.37
    Activations Density 0.658%

    No Known Activations