© 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. 515
    Prev
    Next
    INDEX
    Explanations

    eligibility and time

    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
     Premiership
    -0.30
    ä½ıæĪ¿åħ¬ç§¯
    -0.29
     Playoff
    -0.26
    ｡
    -0.26
    åĶIJå®ĩ
    -0.25
    è¿ĶåĽŀæIJľçĭIJ
    -0.25
    æŁ¥çľĭ详æĥħ
    -0.24
     ******************************************************************************↵
    -0.24
     dequeueReusableCellWithIdentifier
    -0.24
     Jerseys
    -0.24
    POSITIVE LOGITS
     automatically
    0.26
    åı¯ä»¥éĢīæĭ©
    0.25
    %"><
    0.25
     ragazzo
    0.25
    è§Ħå®ļçļĦ
    0.24
    æĸ¹åı¯
    0.24
     grace
    0.24
    èĩªåĬ¨
    0.24
    è§Ĩ
    0.24
     specified
    0.24
    Activations Density 3.837%

    No Known Activations