© 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. 2599
    Prev
    Next
    INDEX
    Explanations

    problems or issues

    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
    obra
    -0.21
     possibilities
    -0.20
    _literals
    -0.19
    ActivityResult
    -0.19
    //↵↵↵
    -0.19
    .ClientSize
    -0.19
    RelativeLayout
    -0.18
    OLLOW
    -0.18
    .getContentPane
    -0.18
    سط
    -0.17
    POSITIVE LOGITS
    æŁIJäºĽ
    0.27
    Calibri
    0.26
    æľīæŶ
    0.25
    Certain
    0.23
    çļĦéĹ®é¢ĺ
    0.23
    åģ¶å°Ķ
    0.23
    .ToShort
    0.22
    [âĢ¦
    0.22
     certain
    0.22
    ðŁIJĽ
    0.22
    Activations Density 1.121%

    No Known Activations