© 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. 51240
    Prev
    Next
    INDEX
    Explanations

    interrogation and torture

    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
    游æĪıè§Ĵèī²
    -0.09
    æݧ
    -0.09
    好人
    -0.09
    vor
    -0.09
    éĢµ
    -0.09
    MBER
    -0.08
    çļĦåĬŁèĥ½
    -0.08
     волн
    -0.08
    æ¨
    -0.08
    ìłķ
    -0.08
    POSITIVE LOGITS
    室
    0.09
    å¨ģ
    0.09
    åĪĽéĢłåĩº
    0.09
    黳
    0.08
    çĭŀ
    0.08
    æľ¬æľŁ
    0.08
    æĢ§æĦŁ
    0.08
    åĽ½åĢº
    0.08
    uring
    0.08
    éĢ¼è¿ij
    0.08
    Activations Density 0.012%

    No Known Activations