© 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. 366
    Prev
    Next
    INDEX
    Explanations

    product features

    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
    é»ijæģ¶
    -0.28
    å¥ĸåѦ
    -0.28
    治好
    -0.26
    âĪĸ
    -0.26
    游æĪıæĬĢå·§
    -0.26
    èĤĦ
    -0.25
    æĪķ
    -0.24
    讹
    -0.24
    iPad
    -0.24
     Rolex
    -0.24
    POSITIVE LOGITS
    -toast
    0.32
     Erectile
    0.31
     roma
    0.31
    č↵↵
    0.30
    建档ç«ĭ
    0.30
    /antlr
    0.29
    synthesize
    0.29
     misog
    0.28
    ä¸Ģèĩ´å¥½è¯Ħ
    0.27
    VertexAttrib
    0.27
    Activations Density 6.025%

    No Known Activations