© 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. 3247
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    åħ¶å®ĥéĹ®é¢ĺ
    -0.21
     PROGMEM
    -0.21
    åĪĽå®¢
    -0.20
    ç»ı纬
    -0.20
    æľºç»Ħ
    -0.20
    éĵĭ
    -0.19
    cidade
    -0.19
    	volatile
    -0.18
     Rodgers
    -0.18
    .userInteractionEnabled
    -0.18
    POSITIVE LOGITS
    piler
    0.28
     ×Ķ×ķ×ĵ
    0.25
    ocrat
    0.24
    strcasecmp
    0.22
    nü
    0.22
    .UIManager
    0.21
    .ToArray
    0.21
    raquo
    0.21
    é²±
    0.20
    apesh
    0.20
    Activations Density 0.001%

    No Known Activations