© 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. 18515
    Prev
    Next
    INDEX
    Explanations

    who followed by 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
    éĤ£æĺ¯
    -0.13
    说æĺ¯
    -0.11
    æĪij说
    -0.10
    è¿Ļæĺ¯ä¸Ģç§į
    -0.09
    æīįæĺ¯
    -0.09
    æŁĦ
    -0.09
    æŀ¥
    -0.09
    ä»ĸ们æĺ¯
    -0.09
    åĵªæĢķ
    -0.09
     themselves
    -0.09
    POSITIVE LOGITS
    åĴ¨
    0.09
    çĶ±æѤ
    0.09
    ought
    0.09
    åĴ¨è¯¢
    0.09
    OTO
    0.08
    اذ
    0.08
    æģĴ大
    0.08
    maf
    0.08
    åħ¨éĿ¢åıijå±ķ
    0.08
    ANE
    0.08
    Activations Density 0.164%

    No Known Activations