© 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. 5218
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns (their, his, its)

    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
    åĽłä¸ºä½ł
    -0.10
    åİ
    -0.10
    ãĥĥãĤ·
    -0.09
    饱åĴĮ
    -0.09
    IMS
    -0.09
    ays
    -0.09
    æĪij们åºĶ该
    -0.09
    å§ĭ
    -0.09
     lac
    -0.08
    å°¤
    -0.08
    POSITIVE LOGITS
    èĩªå·±åĸľæ¬¢
    0.12
    åıĬåħ¶
    0.09
     its
    0.09
    滿
    0.09
    æľīåĩłä¸ª
    0.09
    Extras
    0.09
    èle
    0.09
    èĩªå·±çļĦ
    0.08
    åīįæīĢæľªæľī
    0.08
    èĩªèº«çļĦ
    0.08
    Activations Density 0.076%

    No Known Activations