© 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. 36468
    Prev
    Next
    INDEX
    Explanations

    as followed by a noun or 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
    å±ŀ
    -0.10
    æī¾åĩº
    -0.09
    utility
    -0.09
    åĩºäºĨ
    -0.09
    ite
    -0.09
    æĬĴ
    -0.09
    pers
    -0.08
    -addon
    -0.08
    åIJĵ
    -0.08
    åĽŀé¦ĸ
    -0.08
    POSITIVE LOGITS
    å¾ħãģ¡
    0.09
    çļĦè¿ĽæŃ¥
    0.09
    çįŃ
    0.09
    ãģ°ãģĭãĤĬ
    0.09
    ä¹Łæĺ¯ä¸Ģç§į
    0.09
     Phaser
    0.09
    éĴĪ对æĢ§
    0.09
    ä¸Ģ種
    0.09
    å®ŀåľ¨
    0.08
    å¥Ķèµ´
    0.08
    Activations Density 0.197%

    No Known Activations