© 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. 3254
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
    /Dk
    -0.29
    -Cs
    -0.27
    :normal
    -0.26
    &o
    -0.24
    idebar
    -0.23
    )||(
    -0.23
    PMC
    -0.23
    æĢ»èĢĮè¨Ģ
    -0.23
    иÑĩеÑģ
    -0.23
    ].'
    -0.23
    POSITIVE LOGITS
    éĿŀ常æĺİæĺ¾
    0.19
     can
    0.18
    aucoup
    0.18
     subpo
    0.18
    身
    0.18
     Pruitt
    0.18
    å®Ī
    0.18
    quette
    0.18
    @end
    0.18
     metav
    0.18
    Activations Density 0.025%

    No Known Activations