© 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. 36587
    Prev
    Next
    INDEX
    Explanations

    over, on, lying

    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
    å½Ģ
    -0.12
    å¢Ļå£ģ
    -0.11
    odor
    -0.10
    ALLE
    -0.10
    æ®ļ
    -0.10
    åĩºåı£
    -0.10
    amespace
    -0.10
    alle
    -0.09
    åĩ¡æľ¬ç½ij
    -0.09
    彪
    -0.09
    POSITIVE LOGITS
    åİĭ
    0.17
    å£ĵ
    0.12
     Äijè
    0.11
    碾
    0.11
    åİĭåĪ¶
    0.11
     over
    0.10
     над
    0.10
     pressing
    0.10
    踩
    0.10
    åİĭè¿«
    0.10
    Activations Density 0.114%

    No Known Activations