© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40059
    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
    uds
    -0.09
    为åħ¶
    -0.09
    辨åĪ«
    -0.09
    ense
    -0.09
    _DL
    -0.08
    wallet
    -0.08
    çİ°è¡Į
    -0.08
    åħ¥å¸Ĥ
    -0.08
     SB
    -0.08
    udy
    -0.08
    POSITIVE LOGITS
    çĶ¨æĪ·æıIJä¾Ľ
    0.11
    éĻĦè¿ijçļĦ
    0.10
    çĶ¨æĪ·çļĦ
    0.09
    æľĭåıĭ们
    0.09
    æīĢåľ¨çļĦ
    0.09
    主管éĥ¨éŨ
    0.09
    éĤ»å±ħ
    0.09
    å¥ĩå¼Ĥ
    0.09
    客æĪ·æıIJä¾Ľ
    0.09
    æīĢåľ¨
    0.09
    Activations Density 0.186%

    No Known Activations