© 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. 51559
    Prev
    Next
    INDEX
    Explanations

    notary, registration, revenue, mortgage, pay

    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
    æŁĶæĢ§
    -0.10
    æģ¯æģ¯
    -0.10
    fern
    -0.09
     wholes
    -0.09
    ä¸ĩ家
    -0.09
    ç²ij
    -0.09
    çIJ´
    -0.09
    æĦĨ
    -0.09
    解
    -0.09
    efault
    -0.09
    POSITIVE LOGITS
    åľŁåľ°
    0.10
    åį°èĬ±
    0.09
    æĺİç¡®äºĨ
    0.09
    PF
    0.09
    agt
    0.09
    æĿŀ
    0.09
    åħ¬è¯ģ
    0.09
    åºĨ
    0.08
    æħ¶
    0.08
    å¤ĩæĪĺ
    0.08
    Activations Density 0.022%

    No Known Activations