© 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. 21943
    Prev
    Next
    INDEX
    Explanations

    you know / you've heard / you're familiar

    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
    è¾ĵç»Ļ
    -0.08
    èģĮ
    -0.08
    ä¸ŃåİŁ
    -0.08
     Norris
    -0.08
    åħĪè¿Ľ
    -0.08
    äºĭåħĪ
    -0.08
    æıIJåīį
    -0.08
    æīĵçĿĢ
    -0.08
    åĪ¶æĪIJ
    -0.08
     Ballard
    -0.08
    POSITIVE LOGITS
     probably
    0.12
     perhaps
    0.11
    æĪĸ许
    0.10
    ãģĬãģĿãĤīãģı
    0.10
    probably
    0.10
    æĥ³å¿ħ
    0.10
    å¹½
    0.10
    ä¹Łè®¸
    0.10
    ä¹Łè®¸æĺ¯
    0.09
    å¾Īåı¯èĥ½
    0.09
    Activations Density 0.043%

    No Known Activations