© 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. 58066
    Prev
    Next
    INDEX
    Explanations

    possessive 's 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
     доволÑĮ
    -0.10
    æģ¨ä¸įå¾Ĺ
    -0.09
    cus
    -0.09
    渡
    -0.09
    åīįçŀ»
    -0.09
    çĥ¦æģ¼
    -0.09
    ä¼ĺç§ĢçļĦ
    -0.08
    ä¸ĵå¿ĥ
    -0.08
    .erb
    -0.08
    红楼
    -0.08
    POSITIVE LOGITS
    çīŁ
    0.10
    æĺ¯ä¸ĢåIJį
    0.08
    æѤåīį
    0.08
    Ñģи
    0.08
     ÑĢанее
    0.08
    å±ħ家
    0.08
    çĪ±ç¾İ
    0.08
    orts
    0.07
    æĻĵå¾Ĺ
    0.07
    ä¸ĢåIJį
    0.07
    Activations Density 0.196%

    No Known Activations