© 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. 35885
    Prev
    Next
    INDEX
    Explanations

    Needless to say

    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
    çĹĶ
    -0.10
    usher
    -0.10
    主ä¹īæĢĿæĥ³
    -0.10
    eel
    -0.09
    (enc
    -0.09
    ÑĢог
    -0.09
    urate
    -0.09
    æĹ¢
    -0.09
    isex
    -0.09
    èģ¿
    -0.09
    POSITIVE LOGITS
    åı¯æĥ³èĢĮçŁ¥
    0.12
    å½ĵçĦ¶æĺ¯
    0.12
    ä¸įçĶ¨
    0.11
    èĩªçĦ¶æĺ¯
    0.10
    ä¸į说
    0.10
    å½ĵçĦ¶
    0.10
    è¿Ļä¹Ī说
    0.10
    åĸ»
    0.09
    说äºĨ
    0.09
     obvious
    0.09
    Activations Density 0.028%

    No Known Activations