© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52461
    Prev
    Next
    INDEX
    Explanations

    socioeconomic status and class

    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
     Ñĥд
    -0.10
    обоÑĢ
    -0.09
    è¿ĻåIJį
    -0.09
    éĵ¡
    -0.09
    ä¸ĢæŃ¥
    -0.09
    æij
    -0.09
    èĪŁ
    -0.09
     autof
    -0.09
     اÙĦÙħج
    -0.09
    wald
    -0.09
    POSITIVE LOGITS
    éĺ¶å±Ĥ
    0.19
    éĺ¶çº§
    0.16
    éļİ
    0.15
    å¯Įè´µ
    0.12
    è´µæĹı
    0.12
    å¹³æ°ij
    0.11
    家åºŃ
    0.11
    æľīéĴ±
    0.11
    層
    0.10
    è´«åĽ°
    0.10
    Activations Density 0.077%

    No Known Activations