© 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. 55881
    Prev
    Next
    INDEX
    Explanations

    therefore we

    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¸ĢæĬ¹
    -0.09
    ãģĵãģĿ
    -0.09
    åĢĺ
    -0.09
    OI
    -0.08
    天涯
    -0.08
    å±ı
    -0.08
    æľī人
    -0.08
    æ²ı
    -0.08
     Tos
    -0.07
    å½ĵå¹´
    -0.07
    POSITIVE LOGITS
    æīĢ以
    0.30
    æīĢ以æĪij们
    0.26
    æīĢ以ä»ĸ
    0.26
    æīĢä»¥åľ¨
    0.25
    åĽłæѤ
    0.25
     nên
    0.24
    æīĢ以æĪij
    0.23
     поÑįÑĤомÑĥ
    0.22
     therefore
    0.21
     donc
    0.20
    Activations Density 0.190%

    No Known Activations