© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 49990
    Prev
    Next
    INDEX
    Explanations

    contains links

    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
    ä»İä¸Ń
    -0.09
    éĢı
    -0.09
    utow
    -0.09
     ÑĢоли
    -0.08
    ç°ĩ
    -0.08
    è´¯
    -0.08
    ä¿Ŀ
    -0.08
    åĩºèº«
    -0.08
    èĦijæµ·ä¸Ń
    -0.08
     Hel
    -0.08
    POSITIVE LOGITS
    大大å°ıå°ı
    0.13
    çĵł
    0.13
    åľ¨åĨħçļĦ
    0.10
    çİ
    0.10
    太å¤ļçļĦ
    0.10
    æĪijçļĦå¿ĥ
    0.10
    å®ĿèĹı
    0.10
    对äºİæĪij们
    0.10
    ä½ľèĢħæľ¬äºº
    0.10
    åı¯æĢķ
    0.10
    Activations Density 0.211%

    No Known Activations