© 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. 32982
    Prev
    Next
    INDEX
    Explanations

    surely followed by 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
    æĢ§å¼º
    -0.10
     ÑģобÑģÑĤвенно
    -0.08
    appy
    -0.08
    çīĸ
    -0.08
     phot
    -0.08
     phen
    -0.08
    ÑĢоб
    -0.08
    ä¸Ģåı£æ°Ķ
    -0.07
    æ´²
    -0.07
    irse
    -0.07
    POSITIVE LOGITS
    ãģ£ãģ¨
    0.10
    tte
    0.10
    ingly
    0.10
    borg
    0.10
     занÑıÑĤ
    0.10
    è¿Ļæĺ¯
    0.10
    窿
    0.09
    å½ĵä¹ĭ
    0.09
    è¿Ļ对äºİ
    0.09
    alling
    0.09
    Activations Density 0.005%

    No Known Activations