© 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. 663
    Prev
    Next
    INDEX
    Explanations

    except or including

    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
    çļĦä¸ĢåĪĩ
    -0.30
    å¼Ģå¥ĸç»ĵæŀľ
    -0.27
    -toggler
    -0.27
    reature
    -0.27
    çļĦä¸ĢäºĽ
    -0.25
    iquement
    -0.25
    'icon
    -0.24
    byss
    -0.24
    ä¸ĢåĪĩéĥ½
    -0.24
    :animated
    -0.23
    POSITIVE LOGITS
    ä¸įåIJĮç¨ĭ度
    0.38
     except
    0.32
    _except
    0.28
    æĪĸå¤ļæĪĸå°ij
    0.28
     besides
    0.26
    except
    0.26
    including
    0.25
     кÑĢоме
    0.25
    åĮħæĭ¬
    0.25
     including
    0.25
    Activations Density 5.410%

    No Known Activations