© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 480
    Prev
    Next
    INDEX
    Explanations

    Possessive pronouns

    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
     the
    -0.21
     of
    -0.21
    ãģıãģªãĤĬãģ¾ãģĹãģŁ
    -0.21
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.21
     things
    -0.20
    幸好
    -0.20
    æīĭæľºçīĪ
    -0.20
    inherits
    -0.20
     '".
    -0.20
     others
    -0.20
    POSITIVE LOGITS
     own
    0.63
    own
    0.40
    ?"↵↵↵↵
    0.35
     OWN
    0.34
    èĩªå·±çļĦ
    0.32
    OWN
    0.30
     Own
    0.29
    Own
    0.28
     +=↵
    0.27
    =""/>↵
    0.27
    Activations Density 1.679%

    No Known Activations