© 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. 6579
    Prev
    Next
    INDEX
    Explanations

    specific activities and conditions

    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
    èĺħ
    -0.10
    steen
    -0.10
    移åĪ°
    -0.10
    æIJĤ
    -0.09
    åł¡
    -0.09
    lesi
    -0.09
    éĶ±
    -0.09
    ä¿Ŀä¿®
    -0.09
    åĶ®åIJİ
    -0.08
    roz
    -0.08
    POSITIVE LOGITS
    符åIJĪæĿ¡ä»¶
    0.14
    é¢ģåıij
    0.13
    çĶ³è¯·
    0.11
    æĵģ
    0.10
    åIJĪæ³ķ
    0.10
    æĮģ
    0.10
     اÙĦدÙĪÙĦØ©
    0.09
    çĶ³è¯·äºº
    0.09
    æ³ķå®ļ
    0.09
    æĭ¥
    0.09
    Activations Density 0.169%

    No Known Activations