© 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. 3279
    Prev
    Next
    INDEX
    Explanations

    what is

    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
     ×Ķ×ķ×ĵ
    -0.28
    æĺ¯ä¸Ģä½į
    -0.23
    åıªæĺ¯
    -0.21
    благо
    -0.21
    æĺ¯ä¸Ģ项
    -0.21
    æĺ¯æĪij
    -0.20
    âĩIJ
    -0.20
    æĺ¯æĪijåĽ½
    -0.20
    IKE
    -0.20
    åıªä¸º
    -0.20
    POSITIVE LOGITS
    羣æŃ£çļĦ
    0.20
    羣æŃ£
    0.20
    æĻ°
    0.20
    åĮºåĪ«
    0.20
    InitialState
    0.19
    ä½łåºĶ该
    0.19
    大å¤ļæķ°
    0.19
    大å¤ļ
    0.19
    ç»Ń
    0.18
    æĪij们è¦ģ
    0.18
    Activations Density 0.361%

    No Known Activations