© 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. 26155
    Prev
    Next
    INDEX
    Explanations

    prejudice and phobia terms

    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
    èĬ«
    -0.09
    å¾ģæľį
    -0.09
    rag
    -0.09
    绽
    -0.09
    ç§Ń
    -0.08
    iverse
    -0.08
     Nope
    -0.08
    amble
    -0.08
    æ´¾
    -0.08
    éĿłè¿ij
    -0.08
    POSITIVE LOGITS
    æģ¯
    0.09
    éĤ¸
    0.09
     Parliamentary
    0.09
    èı©æıIJ
    0.09
    @dynamic
    0.09
    .Execution
    0.08
    ç½Ķ
    0.08
    ting
    0.08
    ven
    0.08
    ä¸Ģé¢Ĺ
    0.08
    Activations Density 0.005%

    No Known Activations