© 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. 17618
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and 'of'

    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
     Chatt
    -0.10
    ä¸įå¼Ģ
    -0.09
    orate
    -0.09
    ä¸İåħ¶
    -0.08
     sayılı
    -0.08
    amation
    -0.08
    åıĸè¯ģ
    -0.08
    æ¶Ĥ
    -0.08
    èĭ±çī¹
    -0.08
    .characters
    -0.08
    POSITIVE LOGITS
     ours
    0.28
     yours
    0.26
     hers
    0.24
     mine
    0.24
     theirs
    0.24
    mine
    0.21
    èĩªå·±çļĦ
    0.18
     Yours
    0.18
    Mine
    0.18
     Mine
    0.18
    Activations Density 0.036%

    No Known Activations