© 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. 2958
    Prev
    Next
    INDEX
    Explanations

    code and documents

    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
    getStatusCode
    -0.20
    (pat
    -0.20
    NumberFormatException
    -0.20
    <=$
    -0.20
    cdecl
    -0.19
    .EndsWith
    -0.19
    :\/\/
    -0.19
    _under
    -0.19
    acos
    -0.19
    éĦľ
    -0.19
    POSITIVE LOGITS
    ialect
    0.26
    bourne
    0.22
    .Glide
    0.20
     Ortiz
    0.20
    +"<
    0.20
    ä»»ä½ķå½¢å¼ı
    0.20
    å©ļ
    0.19
    'email
    0.19
    å¸Į
    0.18
    iffany
    0.18
    Activations Density 0.001%

    No Known Activations