© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58114
    Prev
    Next
    INDEX
    Explanations

    racial, race, racism

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å¯ĵ
    -0.10
    çªĸ
    -0.09
    çĩĬ
    -0.09
    åİĤåĮº
    -0.09
    omid
    -0.09
    对ä¼ģä¸ļ
    -0.09
    доб
    -0.09
    æ®ĩ
    -0.09
    ç§ĺ
    -0.09
    æĨ¬
    -0.09
    POSITIVE LOGITS
    ç§įæĹı
    0.11
     racially
    0.10
     race
    0.10
    èĤ¤èī²
    0.10
     Race
    0.10
     racial
    0.09
    unity
    0.09
    bir
    0.09
    rac
    0.09
     bir
    0.09
    Activations Density 0.172%

    No Known Activations