© 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. 3114
    Prev
    Next
    INDEX
    Explanations

    0

    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
     later
    -0.31
    Later
    -0.28
    later
    -0.27
     Later
    -0.24
     today
    -0.23
    æĥ´
    -0.23
    è¿ijæĹ¥
    -0.22
    ä»Ĭ天
    -0.22
    ä¹ĭåIJİ
    -0.22
    âĪ¬
    -0.22
    POSITIVE LOGITS
    两年åīį
    0.22
    åݻ年
    0.21
    íĶĦë¡ľê·¸
    0.20
     ADVISED
    0.20
    ä¸Ĭå¹´
    0.20
    ereotype
    0.20
    åĩłå¹´åīį
    0.20
    preci
    0.20
    æĿ¨æ¬¢
    0.20
    åIJĮç±»
    0.19
    Activations Density 0.461%

    No Known Activations