© 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. 7883
    Prev
    Next
    INDEX
    Explanations

    game elements

    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
    åŁºè¾ħ
    -0.10
     tattoos
    -0.08
    份é¢Ŀ
    -0.08
    عر
    -0.08
    llu
    -0.08
    åĪ¤
    -0.08
     Atlas
    -0.08
    иÑĢÑĥ
    -0.08
     atlas
    -0.08
    _wheel
    -0.08
    POSITIVE LOGITS
    ä¼Ļ
    0.10
    èĭ
    0.09
    ates
    0.09
    çļĦè®°å¿Ĩ
    0.09
    å¹´é¾Ħ段
    0.09
    æ®ĸ
    0.08
    åĸĺ
    0.08
    éĢĥçĶŁ
    0.08
    Synopsis
    0.08
    æij§æ¯ģ
    0.08
    Activations Density 0.122%

    No Known Activations