© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3628
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     earthqu
    -0.27
    妤
    -0.25
     ragaz
    -0.25
    há»ķ
    -0.24
    paralleled
    -0.24
    acists
    -0.24
     piger
    -0.23
     mụ
    -0.23
     bụ
    -0.23
    åľ¨ä¼łå¥ĩ
    -0.23
    POSITIVE LOGITS
     this
    0.24
    è¿Ļ家åħ¬åı¸
    0.22
    æİĸ
    0.22
    __("
    0.21
    æĶ¯çIJĥéĺŁ
    0.20
     and
    0.20
     or
    0.19
    è¿Ļ个è¡Įä¸ļ
    0.19
    çļĦåĪ©çĽĬ
    0.18
    æŃ¤é¡¹
    0.18
    Activations Density 1.245%

    No Known Activations