© 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. 1292
    Prev
    Next
    INDEX
    Explanations

    general things

    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
     subparagraph
    -0.30
     erotica
    -0.30
     (*((
    -0.26
    çĶŃ
    -0.26
    幸好
    -0.25
    âĢ½
    -0.24
    åĨµä¸Ķ
    -0.24
    figcaption
    -0.24
    çĽ¸ä¿¡å¤§å®¶
    -0.24
     cunt
    -0.23
    POSITIVE LOGITS
     stuff
    0.37
     things
    0.30
    âĨ©
    0.28
    ä¹ĭç±»
    0.27
     __________________↵↵
    0.27
     pretty
    0.27
     thing
    0.27
    âĪİ
    0.26
    çĭŀ
    0.26
    INLINE
    0.26
    Activations Density 12.213%

    No Known Activations