© 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. 1852
    Prev
    Next
    INDEX
    Explanations

    legal 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
    expectException
    -0.22
    .PostMapping
    -0.22
    QRST
    -0.21
    swire
    -0.20
    ercul
    -0.20
    Elite
    -0.20
    usterity
    -0.20
    =pk
    -0.19
    hof
    -0.19
    ushman
    -0.19
    POSITIVE LOGITS
     supra
    0.24
    窸
    0.19
    å¼Ľ
    0.19
    :relative
    0.19
    $conn
    0.18
    0.18
    车éĺŁ
    0.18
     aff
    0.18
     published
    0.17
    诺
    0.17
    Activations Density 0.346%

    No Known Activations