© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 322
    Prev
    Next
    INDEX
    Explanations

    if

    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
    æĹ¶ä»£ä¸ŃåĽ½
    -0.21
    entiful
    -0.21
    /alert
    -0.20
     Dodge
    -0.20
    stdClass
    -0.20
     $("<
    -0.20
    éĢĨ
    -0.20
    -middle
    -0.19
    ersed
    -0.19
     Burgess
    -0.19
    POSITIVE LOGITS
     not
    0.29
     !
    0.28
    ');↵↵↵↵
    0.27
     isinstance
    0.27
     !(
    0.25
    è¹ģ
    0.25
    ä¸įæĺ¯
    0.24
    not
    0.24
    rame
    0.24
    |array
    0.22
    Activations Density 0.199%

    No Known Activations