© 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. 21545
    Prev
    Next
    INDEX
    Explanations

    a [noise, nano, transmission, thicker, distributed, inner, control, touch, user, leakage]

    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
    æ§ģ
    -0.08
    éļıæīĭ
    -0.08
     Jeans
    -0.08
    åĴĮå¹³
    -0.08
    zhou
    -0.08
     Bird
    -0.07
    åĨĴ
    -0.07
    æĻĴ
    -0.07
    è¿Ŀ
    -0.07
    plaintext
    -0.07
    POSITIVE LOGITS
    è¿Ļæīįæĺ¯
    0.11
    å¤ļå±Ĥ次
    0.11
    ugin
    0.10
    èĪĮ
    0.09
    ãģ¦ãģĦ
    0.09
    ä¿¡å¿ĥ
    0.09
    ä¸İæѤ
    0.09
    äºĨåIJĹ
    0.09
    æݧåĪ¶ç³»ç»Ł
    0.09
    è¿Ļæīį
    0.09
    Activations Density 0.667%

    No Known Activations