© 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. 36233
    Prev
    Next
    INDEX
    Explanations

    own right / in itself

    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
    容å¿į
    -0.09
    à¸IJ
    -0.09
     Remed
    -0.09
    åķĨä¸ļåĮĸ
    -0.08
     Hamp
    -0.08
    iliate
    -0.08
    èĦ¸èī²
    -0.08
    天èµĭ
    -0.08
    åĶ¯ä¸ĢçļĦ
    -0.08
    åĿIJæłĩ
    -0.08
    POSITIVE LOGITS
     itself
    0.23
    æľ¬èº«
    0.21
    æľ¬èº«çļĦ
    0.18
     themselves
    0.16
    æľ¬èº«å°±æĺ¯
    0.16
    æľ¬èº«å°±
    0.16
    èĩªèº«çļĦ
    0.16
    èĩªèº«
    0.15
     herself
    0.14
     ìŀIJì²´
    0.14
    Activations Density 0.092%

    No Known Activations