© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6699
    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
     det
    -0.09
    åħ¶å®ĥ
    -0.09
    ensex
    -0.09
    åħ¶ä»ĸ
    -0.08
    Ñĥнк
    -0.08
     horn
    -0.08
    ÙĤع
    -0.08
    åı¦ä¸Ģæĸ¹éĿ¢
    -0.08
    ect
    -0.08
    éī´åĪ«
    -0.08
    POSITIVE LOGITS
    å¦Ĥæŀľæĺ¯
    0.09
     Alv
    0.09
    鹤
    0.08
    çĿĢæīĭ
    0.08
     Dwight
    0.08
    箪
    0.08
    æıIJä¾Ľä¼ĺè´¨
    0.08
     Ñģеб
    0.08
    ä»ħä»ħæĺ¯
    0.08
    带é¢Ĩ
    0.08
    Activations Density 0.270%

    No Known Activations