© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30526
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ç®į
    -0.09
    uale
    -0.09
    AnimationFrame
    -0.08
    åĨ·ç¬ij
    -0.08
    èķĻ
    -0.08
    ä¸ĵ
    -0.08
    سÙģ
    -0.08
    è§ĴèIJ½
    -0.08
    æ³ķåĪĻ
    -0.08
    çļĦ人æĿ¥è¯´
    -0.08
    POSITIVE LOGITS
     Gerard
    0.09
    ä¹ĸä¹ĸ
    0.09
    溱
    0.08
     OWN
    0.08
    æ£Ĵ
    0.08
    RAY
    0.08
    -blind
    0.08
    å©¢
    0.08
    æ¤ħåŃIJ
    0.08
     Watt
    0.08
    Activations Density 0.010%

    No Known Activations