© 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. 33707
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

    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
    å¸ĺ
    -0.09
    illo
    -0.08
    åħĭ
    -0.08
     Horn
    -0.08
    ingles
    -0.08
    赦
    -0.08
     undecided
    -0.08
    Standing
    -0.07
    è¿Ļåĩłä¸ª
    -0.07
    çģµ
    -0.07
    POSITIVE LOGITS
    åħ¬åı¸åľ¨
    0.14
    éĥ¨éĸĢ
    0.14
    éĥ¨éŨ
    0.14
    éĥ¨éĺŁ
    0.13
    æīĢåľ¨çļĦ
    0.13
    æīĢåľ¨
    0.12
    çIJĥéĺŁ
    0.12
    ä¼ģä¸ļåľ¨
    0.11
    åħ¬åı¸å°Ĩ
    0.11
    麾
    0.11
    Activations Density 0.073%

    No Known Activations