© 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. 11917
    Prev
    Next
    INDEX
    Explanations

    after once

    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
    éļıæŶ
    -0.10
    onium
    -0.10
    ä¸Ģé¡¿
    -0.10
    åĩ«
    -0.09
    éĤ£å°±æĺ¯
    -0.09
     ØŃاÙĦ
    -0.09
    ä¸ĢèĪ¬æĿ¥è¯´
    -0.09
    åĢ¼å¾Ĺä¸Ģ
    -0.09
    son
    -0.09
    ä¹ĭæīĢ
    -0.09
    POSITIVE LOGITS
    åħ¶
    0.10
    eve
    0.10
    å°ĺ
    0.10
    æİ¥åĪ°
    0.09
    ìĶ©
    0.09
    /if
    0.09
    fy
    0.09
    碰åĪ°
    0.09
    arily
    0.09
    çĿĢæīĭ
    0.09
    Activations Density 0.013%

    No Known Activations