© 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. 1442
    Prev
    Next
    INDEX
    Explanations

    Cro

    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
    åħ¶å®ĥéĹ®é¢ĺ
    -0.33
    æĢ§ä»·
    -0.33
    CLUDING
    -0.30
    åľ¨è¿ĩ渡
    -0.30
    åı¯ä»¥æĽ´å¥½
    -0.29
    ä»İæł¹æľ¬
    -0.29
     vidé
    -0.29
     Erectile
    -0.28
    æĭľå¸ĪåѦèīº
    -0.28
    <Renderer
    -0.27
    POSITIVE LOGITS
     bénéficie
    0.25
     suche
    0.24
    ÙģØ°
    0.24
    باÙĥ
    0.23
    -quarters
    0.23
     schöne
    0.22
     lokale
    0.22
    ccoli
    0.22
    teenth
    0.22
    elocity
    0.21
    Activations Density 9.784%

    No Known Activations