© 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. 3500
    Prev
    Next
    INDEX
    Explanations

    approaching soon

    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
    çīĪæĿĥå½Ĵ
    -0.21
     newly
    -0.18
     completion
    -0.18
    ennen
    -0.18
     upt
    -0.18
    çĽ¸å¹²
    -0.18
    Contin
    -0.17
     GIVEN
    -0.17
    			č↵			č↵
    -0.17
    ync
    -0.17
    POSITIVE LOGITS
    临è¿ij
    0.26
     imminent
    0.25
    åį³å°Ĩ
    0.25
    æĿ¥ä¸´
    0.25
    :numel
    0.24
     approaches
    0.24
     Appro
    0.24
    çļĦåĪ°æĿ¥
    0.23
    åĪ°æĿ¥
    0.23
     soon
    0.22
    Activations Density 0.485%

    No Known Activations