© 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. 35883
    Prev
    Next
    INDEX
    Explanations

    get [comparative/quantitative adjective]

    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
    istine
    -0.09
    çĤ¹åĩ»æŁ¥çľĭ
    -0.09
    æľĢé«ĺçļĦ
    -0.09
    æ¯Ķè¾ĥ
    -0.08
    æĸ¹ä½į
    -0.08
    帷
    -0.08
    éŃĶ鬼
    -0.08
     rag
    -0.08
    ILLE
    -0.08
    èĨĢ
    -0.08
    POSITIVE LOGITS
    åıĺå¾ĹæĽ´
    0.17
    åıĺå¾ĹæĽ´åĬł
    0.15
    åıĺå¾Ĺ
    0.14
    è®Ĭå¾Ĺ
    0.13
    /gpl
    0.11
    åħħ
    0.10
    æ¡Ī
    0.10
    åĿļä¿¡
    0.10
    åħħå®ŀ
    0.10
    è¶ĬæĿ¥è¶Ĭ好
    0.10
    Activations Density 0.112%

    No Known Activations