© 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. 3490
    Prev
    Next
    INDEX
    Explanations

    .

    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
    âļĹ
    -0.30
    .za
    -0.28
    grily
    -0.27
    /Dk
    -0.24
    emarks
    -0.23
    AllWindows
    -0.23
     Rencontres
    -0.23
    âĹĤ
    -0.23
    riday
    -0.23
    Hôtel
    -0.23
    POSITIVE LOGITS
     defe
    0.21
    getRepository
    0.20
     Stern
    0.19
    .getById
    0.18
    ÙĬا
    0.18
    .setSize
    0.18
     arithmetic
    0.18
    Ñĥни
    0.18
    çݰ代çī©æµģ
    0.18
     AAA
    0.18
    Activations Density 0.021%

    No Known Activations