© 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. 49359
    Prev
    Next
    INDEX
    Explanations

    who 've | experienced | lost | travel | are | occupy | is

    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
    åı¯ä»¥è¯´
    -0.09
    åĽłåľ°
    -0.08
     himself
    -0.08
    å¥Ĥ
    -0.08
    _sf
    -0.08
    骥
    -0.08
    ä»Ĭ天æĪij们
    -0.08
    æľīä¸Ģä½į
    -0.08
    æķı
    -0.07
    å°±æĺ¯ä¸Ģ个
    -0.07
    POSITIVE LOGITS
    æݥ触
    0.13
    æݥ触åĪ°
    0.12
    æĮŀ
    0.10
    èºģ
    0.10
    åĵº
    0.10
    å´¤
    0.10
    æĻļ
    0.09
    æħķ
    0.09
    è³¼
    0.09
    觸
    0.09
    Activations Density 0.059%

    No Known Activations