© 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. 3443
    Prev
    Next
    INDEX
    Explanations

    latest updates

    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
    æīŃ转
    -0.19
     lucr
    -0.19
    htmlspecialchars
    -0.18
    ä¹łæĥ¯äºĨ
    -0.18
    (horizontal
    -0.18
    /ne
    -0.17
    è§Ħ模åĮĸ
    -0.17
    åĪĨ级
    -0.17
    ำ
    -0.17
    sek
    -0.17
    POSITIVE LOGITS
    æĽ´æĸ°
    0.57
     updates
    0.48
    æľĢæĸ°çļĦ
    0.47
     update
    0.47
     updating
    0.46
     updated
    0.46
     æĽ´æĸ°
    0.45
    æľĢæĸ°
    0.44
    ä¸İæĹ¶ä¿±è¿Ľ
    0.43
     latest
    0.41
    Activations Density 0.752%

    No Known Activations