© 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. 56160
    Prev
    Next
    INDEX
    Explanations

    possessive determiners 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
     extrad
    -0.11
    æĶ¸
    -0.11
    éĢļéģĵ
    -0.11
    æĸĻ
    -0.10
     disconnect
    -0.09
    壶
    -0.09
    åĪĿ级
    -0.09
    æ²¥
    -0.09
    ilion
    -0.09
    æĢģ度
    -0.09
    POSITIVE LOGITS
    æѦæŀĹ
    0.09
    edList
    0.09
     ping
    0.08
     велик
    0.08
    é«ĺæķĪçļĦ
    0.08
    çĵĺ
    0.08
    Granted
    0.08
     Granted
    0.08
    人工
    0.08
    é¹°
    0.08
    Activations Density 0.022%

    No Known Activations