© 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. 710
    Prev
    Next
    INDEX
    Explanations

    at locations or venues

    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
    è§Ħ模æľĢ大
    -0.11
    å¹´èĸª
    -0.10
    æī¶è´«å·¥ä½ľ
    -0.09
    å¾Ģä¸ĭ
    -0.08
    é»ĺ
    -0.08
    è¿ĩåİ»äºĨ
    -0.08
    åħ¨çIJĥæľĢ大
    -0.08
    волÑĮ
    -0.08
    onas
    -0.08
    asaki
    -0.08
    POSITIVE LOGITS
    åľ°çĤ¹
    0.13
    åľºåľ°
    0.12
     venue
    0.11
    主æĮģåı¬å¼Ģ
    0.11
    游åĩ»
    0.11
     venues
    0.11
    Venue
    0.10
    é¥ŃåºĹ
    0.10
    ä¼ļ议室
    0.10
     location
    0.10
    Activations Density 0.172%

    No Known Activations