© 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. 944
    Prev
    Next
    INDEX
    Explanations

    human memory and cognition

    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
    âĸ¿
    -0.27
    å§ĭ建
    -0.26
     ErrorResponse
    -0.25
    /DD
    -0.25
     RestClient
    -0.24
     arrog
    -0.23
    -scalable
    -0.23
    vron
    -0.23
    çīĪæĿĥå½ĴåİŁ
    -0.23
     beneficiation
    -0.23
    POSITIVE LOGITS
    é»ijæģ¶
    0.30
    -Owned
    0.30
    åºĶæĶ¶è´¦
    0.27
     arousal
    0.26
    éĹ©
    0.25
    纰
    0.25
    ä½ıæĪ¿åħ¬ç§¯
    0.24
    èģĬèģĬ
    0.23
    çªģå¦Ĥåħ¶æĿ¥
    0.23
     cue
    0.23
    Activations Density 3.716%

    No Known Activations