© 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. 27901
    Prev
    Next
    INDEX
    Explanations

    and followed by action verbs

    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
     Hurt
    -0.10
    åı¯ä»¥æł¹æį®
    -0.09
    åıªå¥½
    -0.09
    è¦ģåıĬæŶ
    -0.09
    ä¸ĢäºĽ
    -0.09
    çļĦç¡®
    -0.08
    å°Ĩè¿Ľä¸ĢæŃ¥
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    主æµģ
    -0.08
    æ½®
    -0.08
    POSITIVE LOGITS
    使åħ¶
    0.10
    æĭĵå±ķ
    0.10
    使ä¹ĭ
    0.09
    æİĴéĻ¤
    0.09
    亶
    0.09
     Schn
    0.08
    å¡ijéĢł
    0.08
     sÆ°
    0.08
    оÑĩнÑĭй
    0.08
     Dedicated
    0.08
    Activations Density 0.205%

    No Known Activations