© 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. 40229
    Prev
    Next
    INDEX
    Explanations

    rapper or rap performance

    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
    å¾Īå¤ļçݩ家
    -0.09
    åľ¨ä¸ĢæĹģ
    -0.09
    åıĪä¸Ģ次
    -0.08
    mente
    -0.08
    าà¸ĩ
    -0.08
    agini
    -0.08
    广éĺĶ
    -0.08
    çĪµå£«
    -0.08
    éĤ£è¾¹
    -0.08
     Wage
    -0.08
    POSITIVE LOGITS
    KeyName
    0.09
    æ¶İ
    0.09
    UEL
    0.08
    andel
    0.08
     Respons
    0.08
    æķħ乡
    0.08
    é¾Ļæ¹ĸ
    0.08
    extent
    0.08
    Extent
    0.08
    èĽĶ
    0.08
    Activations Density 0.013%

    No Known Activations