© 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. 36260
    Prev
    Next
    INDEX
    Explanations

    career decisions and success

    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
    æݨ广
    -0.11
    åĬ«
    -0.09
    วà¸ĩ
    -0.09
    è¶³å¤ŁçļĦ
    -0.09
    ä¸Ģå¿ĥ
    -0.08
    ç¢į
    -0.08
    è§ģè¯ģ
    -0.08
    ç«Ļ
    -0.08
    ä¸Ģèĩ´æĢ§
    -0.08
     tel
    -0.08
    POSITIVE LOGITS
    å°ĨæĿ¥
    0.17
    æĹ¥åIJİ
    0.13
    æľªæĿ¥
    0.13
    ä¸ĢçĶŁ
    0.13
    future
    0.12
    åľ¨æľªæĿ¥
    0.12
    ç»Ī身
    0.11
    ç»ĪçĶŁ
    0.11
    以åIJİ
    0.11
    ä»ĬåIJİ
    0.11
    Activations Density 0.065%

    No Known Activations