© 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. 893
    Prev
    Next
    INDEX
    Explanations

    identifying experiences attitudes

    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
    /↵↵↵↵
    -0.33
    /MPL
    -0.32
    /stretch
    -0.28
    å§ĭ建
    -0.27
     licensors
    -0.27
    /mit
    -0.26
    注æĺİæĿ¥æºIJ
    -0.26
    åıĸåĨ³
    -0.25
     ÑģÑĢаз
    -0.25
    ðŁĺ¦
    -0.25
    POSITIVE LOGITS
    é¦ĸå¯Į
    0.31
    åĬŀå®ŀäºĭ
    0.28
     dumpsters
    0.28
    对åħ¶çľŁå®ŀ
    0.26
     molec
    0.25
     LoginComponent
    0.24
     disag
    0.24
     tatto
    0.24
    建æŀĦ
    0.23
     ucwords
    0.23
    Activations Density 4.749%

    No Known Activations