© 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. 3233
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    -0.23
    	freopen
    -0.21
    亲çĪ±
    -0.21
    æĮīæij©
    -0.19
    íķĺìĺĢëĭ¤
    -0.19
    jspx
    -0.19
     Quint
    -0.19
     mor
    -0.19
    eced
    -0.19
     guilty
    -0.18
    POSITIVE LOGITS
     (~(
    0.28
     èĭ¥è¦ģ
    0.23
    ederland
    0.23
     //~
    0.23
    大éģĵ
    0.21
    BOSE
    0.21
    产æĿĥ
    0.21
    ðŁĴ¥
    0.20
    UME
    0.20
    ï¿£
    0.20
    Activations Density 0.000%

    No Known Activations