© 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. 19113
    Prev
    Next
    INDEX
    Explanations

    possessive determiners and relationships

    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
     others
    -0.10
    仡
    -0.09
    女çĶŁ
    -0.09
    -0.08
    姿
    -0.08
    å±ĢåĬ¿
    -0.08
    hä
    -0.08
    ç¿Ģ
    -0.08
    ÑĥÑĢ
    -0.08
    女åŃIJ
    -0.08
    POSITIVE LOGITS
    åĶ¯ä¸ĢçļĦ
    0.11
    æĥŁ
    0.10
    ä»Ģä¹Īåij¢
    0.10
    åĶ¯ä¸Ģ
    0.10
    çĤĬ
    0.10
    å¾Ī好çļĦ
    0.10
    å¤ļå¹´çļĦ
    0.09
    çģµæĦŁ
    0.09
    _INFINITY
    0.09
    åĽºå®ļçļĦ
    0.09
    Activations Density 0.036%

    No Known Activations