© 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. 666
    Prev
    Next
    INDEX
    Explanations

    garbled text

    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
     fkk
    -0.23
    çĶį
    -0.23
    CTS
    -0.22
     Natürlich
    -0.21
    ximity
    -0.21
    åıĪ好åıĪå¿«
    -0.20
    /Internal
    -0.20
    篪
    -0.20
    تÙĥÙĪÙĨ
    -0.19
    CREASE
    -0.18
    POSITIVE LOGITS
    çĽĺçĤ¹
    0.20
    adget
    0.20
    Storyboard
    0.18
     predis
    0.18
    ;};↵
    0.18
    ditor
    0.17
    ulings
    0.17
    æ±Łæ¹ĸ
    0.17
    orgeous
    0.17
    èıĬèĬ±
    0.17
    Activations Density 0.001%

    No Known Activations