© 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. 40231
    Prev
    Next
    INDEX
    Explanations

    "no fear no favor"

    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
    ssel
    -0.10
    è·Łå¥¹
    -0.09
     Sle
    -0.09
    èĢ½
    -0.09
    漪
    -0.08
    å°ıå¾®ä¼ģä¸ļ
    -0.08
    延éķ¿
    -0.08
    repeat
    -0.08
    паÑģ
    -0.08
     RR
    -0.08
    POSITIVE LOGITS
    æķ¢
    0.15
    æķ¢äºİ
    0.14
    缴è¨Ģ
    0.13
     Bold
    0.12
    大èĥĨ
    0.11
    éĵ¿
    0.11
    ä¸įçķĻ
    0.11
    强æĤį
    0.11
     bold
    0.10
    强硬
    0.10
    Activations Density 0.170%

    No Known Activations