© 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. 26099
    Prev
    Next
    INDEX
    Explanations

    limited liability company

    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
    åĵģä½į
    -0.10
    çĨ
    -0.10
    å¼ĢåıijèĢħ
    -0.09
    ç©´ä½į
    -0.09
    éľĢæ±Ĥ
    -0.09
    åĵģåij³
    -0.09
    奥è¿IJ
    -0.09
    è·Ĺ
    -0.09
    rol
    -0.09
    otas
    -0.08
    POSITIVE LOGITS
    å·¥åķĨ
    0.10
    æ³ķ人
    0.10
    çĻ»è®°
    0.10
    设ç«ĭ
    0.10
    çĶĺ
    0.09
    å´Ľ
    0.09
     Tre
    0.09
    èĭķ
    0.09
    äººæł¼
    0.09
    ç»ĵæŀĦ
    0.09
    Activations Density 0.057%

    No Known Activations