© 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. 36413
    Prev
    Next
    INDEX
    Explanations

    medical centers, hospitals, and services

    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
    æ´²
    -0.10
     Ñĥзн
    -0.09
    羣æŃ£çļĦ
    -0.09
    èĩ¼
    -0.09
    abay
    -0.09
    umped
    -0.08
     teg
    -0.08
    è¸ıå®ŀ
    -0.08
    åĩºå¢ĥ
    -0.08
    åıijè§ī
    -0.08
    POSITIVE LOGITS
    retty
    0.08
    æ³¥
    0.08
    иÑĤелÑĮно
    0.08
    ä»Ģä¹Īåij¢
    0.08
    aders
    0.08
    pies
    0.08
    èģĶ缣
    0.08
    åįıä¼ļ
    0.08
    çīĪæĿĥå½ĴåİŁ
    0.08
     aforementioned
    0.08
    Activations Density 0.219%

    No Known Activations