© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16572
    Prev
    Next
    INDEX
    Explanations

    the [noun]

    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
    Negative Logits
    ç´§
    -0.10
    èµį
    -0.10
    éľĩæĴ¼
    -0.09
    åīª
    -0.08
     Gol
    -0.08
    踵
    -0.08
    çĵľ
    -0.08
    æıĨ
    -0.08
    ä¸Ģç¬Ķ
    -0.08
    æķĪæŀľ
    -0.08
    POSITIVE LOGITS
    recht
    0.10
    çijŃ
    0.09
    è¿Ļ对
    0.09
     Thorn
    0.08
    çĸ¥
    0.08
    çĶŁæ´»çݯå¢ĥ
    0.08
    ä¸İä¸ŃåĽ½
    0.08
    对ä¸ŃåĽ½
    0.08
     candid
    0.08
     Worship
    0.08
    Activations Density 0.081%

    No Known Activations