© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1336
    Prev
    Next
    INDEX
    Explanations

    websites

    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
    .liferay
    -0.28
    å·¥ä½ľä½ľé£İ
    -0.23
    æľīè¿ĩ
    -0.21
    ç»Ħç»ĩé¢Ĩ导
    -0.21
    á»ģm
    -0.21
    าว
    -0.21
    è¸ıå®ŀ
    -0.20
    åĪ°è¿ĻéĩĮ
    -0.20
    rchive
    -0.19
    æľįåĬ¡èĥ½åĬĽ
    -0.19
    POSITIVE LOGITS
    åĹIJ
    0.29
    kea
    0.27
    uforia
    0.26
    æĢ»èĢĮè¨Ģ
    0.25
    esteem
    0.24
    /Instruction
    0.23
    istrator
    0.23
    åijĶ
    0.23
    :maj
    0.22
    CGPoint
    0.22
    Activations Density 0.239%

    No Known Activations