© 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. 33615
    Prev
    Next
    INDEX
    Explanations

    affirmative action, quotas, wage legislation

    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
    è¯ķæİ¢
    -0.10
    ä¼łè¾¾
    -0.09
    çŃĴ
    -0.09
    ä¸Ģ次
    -0.09
    cia
    -0.09
     наÑģ
    -0.09
    akis
    -0.09
    æī«ä¸Ģ
    -0.09
    ç®ķ
    -0.08
    欲
    -0.08
    POSITIVE LOGITS
    ç¢į
    0.15
    éĻIJåĪ¶
    0.11
    ç¤Ļ
    0.10
    æݪæĸ½
    0.10
    åĩĨåħ¥
    0.10
    éĻIJé¢Ŀ
    0.09
    ç¶
    0.09
    Speaker
    0.09
    çħ§é¡¾
    0.09
    èī¯
    0.09
    Activations Density 0.074%

    No Known Activations