© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2886
    Prev
    Next
    INDEX
    Explanations

    words of commitment

    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
     EVEN
    -0.25
     even
    -0.21
     zwar
    -0.20
    iances
    -0.20
    even
    -0.20
    ">//
    -0.20
    alis
    -0.20
    ableObject
    -0.19
    èĻ½
    -0.19
    Ĭ
    -0.19
    POSITIVE LOGITS
    深交
    0.23
     '../../../../../
    0.23
    óst
    0.23
    -initialized
    0.23
     bü
    0.20
    elaide
    0.20
    /ay
    0.20
    ãİľ
    0.20
    _ATTACHMENT
    0.20
    #echo
    0.19
    Activations Density 0.658%

    No Known Activations