© 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. 4155
    Prev
    Next
    INDEX
    Explanations

    only to verb

    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
    游è§Ī
    -0.09
    èĩ¼
    -0.09
    ä»»ä½ķ人
    -0.09
    enet
    -0.08
    å§Ĭ妹
    -0.08
    èģĶåIJĪä¼ļ
    -0.08
    oser
    -0.08
     Ñĥме
    -0.08
    太太
    -0.08
    åIJĪãģĦ
    -0.08
    POSITIVE LOGITS
    è¿İæĿ¥
    0.14
    è¿İæĿ¥äºĨ
    0.12
    åį´åıijçİ°
    0.12
    åį´
    0.11
    åį´åıĪ
    0.10
    yet
    0.10
    åıĪ被
    0.10
     rá»ĵi
    0.10
    åį´è¢«
    0.10
    ç»ĵæŀľ
    0.09
    Activations Density 0.045%

    No Known Activations