© 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. 59006
    Prev
    Next
    INDEX
    Explanations

    age or society

    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
    æīįåı¯ä»¥
    -0.08
    elman
    -0.08
    æīįèĥ½å¤Ł
    -0.08
    å»Ĭ
    -0.08
     cú
    -0.08
     Chill
    -0.08
    åĩłå¼ł
    -0.08
     Greenwood
    -0.08
    Tyler
    -0.08
    åĴª
    -0.08
    POSITIVE LOGITS
    æĹ¶ä»£
    0.18
    æĹ¶ä»£çļĦ
    0.17
    çݰ代社ä¼ļ
    0.17
    æĻĤ代
    0.16
    çļĦæĹ¶ä»£
    0.16
    æĸ°æĹ¶ä»£
    0.15
     era
    0.15
    è¿Ļ个æĹ¶ä»£
    0.14
     society
    0.12
    å½ĵä»Ĭ
    0.12
    Activations Density 0.080%

    No Known Activations