© 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. 29785
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by family members

    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
    ÑģÑĥ
    -0.10
    æ¶Īè´¹åĵģ
    -0.09
    åĴĮ个人
    -0.09
    为åĩĨ
    -0.08
    æĵį
    -0.08
    -Men
    -0.08
    èŁ
    -0.08
    FM
    -0.08
     amen
    -0.08
    FML
    -0.08
    POSITIVE LOGITS
    ä¹ĸ
    0.11
    çĪ¶æ¯į
    0.10
    家人
    0.10
    åħĦ
    0.10
    éŃĶæľ¯
    0.10
    åIJįåı«
    0.10
    ä¸Ģ家
    0.09
    å§ij
    0.09
    ä¸Ģä½į
    0.09
    æľīä¸Ģä½į
    0.09
    Activations Density 0.088%

    No Known Activations