© 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. 912
    Prev
    Next
    INDEX
    Explanations

    science, humans, universe

    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
    å±Ĥåĩºä¸į
    -0.29
     autoFocus
    -0.27
     onBlur
    -0.27
     onFocus
    -0.26
    è¿Ļä¸ªåľ°åĽ¾
    -0.25
     earthqu
    -0.25
    AndPassword
    -0.25
     molec
    -0.24
     sharedPreferences
    -0.23
     CommandType
    -0.23
    POSITIVE LOGITS
    人类
    0.33
     humans
    0.33
     scientists
    0.30
     human
    0.30
     Earth
    0.29
     billions
    0.28
    ç§ijåŃ¦å®¶
    0.28
     scientific
    0.27
     science
    0.27
     disadv
    0.27
    Activations Density 7.086%

    No Known Activations