© 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. 6562
    Prev
    Next
    INDEX
    Explanations

    socially conservative ideology

    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
    éĴĵé±¼
    -0.11
    åħ¬å¹³
    -0.09
    ä¸įåħ¬å¹³
    -0.09
    -leaning
    -0.08
    æĸ¯åĿ¦
    -0.08
    Č
    -0.08
    åİ¿éķ¿
    -0.08
    殳
    -0.08
    è§Ĥä¼Ĺ
    -0.08
    éĢ®æįķ
    -0.08
    POSITIVE LOGITS
    ihan
    0.09
    çļĦåħ·ä½ĵ
    0.08
    çł¥
    0.08
    ä¹ĭ家
    0.08
     fuck
    0.08
    ç¬
    0.08
    çĥĤ
    0.08
    æ§IJ
    0.07
    iscard
    0.07
    ä¾
    0.07
    Activations Density 0.104%

    No Known Activations