© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51882
    Prev
    Next
    INDEX
    Explanations

    looking into

    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
    ulton
    -0.10
    è°ı
    -0.09
    åº
    -0.09
    íĦ°
    -0.09
     sürekli
    -0.09
     Binder
    -0.09
    aps
    -0.08
    çĦ¦çĤ¹
    -0.08
    emás
    -0.08
    .ops
    -0.08
    POSITIVE LOGITS
    æѤäºĭ
    0.11
    otch
    0.11
    å¹½
    0.10
    å¦Ĥä½ķ
    0.10
    çĶ¨æīĭ
    0.09
    ç¼ĺ
    0.09
    ราว
    0.09
     how
    0.09
    kick
    0.09
    ä»Ģä¹Īæĺ¯
    0.09
    Activations Density 0.010%

    No Known Activations