© 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. 21688
    Prev
    Next
    INDEX
    Explanations

    french words ending in en or em

    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
    raries
    -0.08
    é«ĺå³°
    -0.08
    åĩ¡æĺ¯
    -0.08
     оÑĤдел
    -0.08
     WithEvents
    -0.08
    enge
    -0.07
    _procs
    -0.07
    åıªè¦ģæĺ¯
    -0.07
    çļĦçݰ象
    -0.07
    ÑĤин
    -0.07
    POSITIVE LOGITS
    身为
    0.10
    ä¸Ģ身
    0.10
    ocha
    0.09
    æĪĸå¤ļ
    0.09
    å°Ŀ
    0.09
    æijĶ
    0.09
    è¾ŀ
    0.09
    wner
    0.09
    æĹ·
    0.09
    ictim
    0.08
    Activations Density 0.022%

    No Known Activations