© 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. 18451
    Prev
    Next
    INDEX
    Explanations

    Egypt, Academy, union, Delta, sixth, Post

    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
    æŃ£å¸¸ä½¿çĶ¨
    -0.11
    æŃ£å¸¸çļĦ
    -0.10
    è¢Ĥ
    -0.10
    çī¹æ´¾åijĺ
    -0.09
    è²Ŀ
    -0.09
    微信åı·
    -0.09
    è£ĺ
    -0.09
    èĪĤ
    -0.09
     cud
    -0.09
    ä¸Ģè¶Ł
    -0.09
    POSITIVE LOGITS
    èįIJ
    0.09
    ller
    0.08
    aco
    0.08
    åħ«å¤§
    0.08
    å°¸
    0.08
    ialect
    0.08
    ppers
    0.08
    èıĬèĬ±
    0.08
     coc
    0.08
     вн
    0.08
    Activations Density 0.085%

    No Known Activations