© 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. 18304
    Prev
    Next
    INDEX
    Explanations

    numbers and phone numbers

    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
    nero
    -0.10
    å»īä»·
    -0.09
    owie
    -0.09
    ãģ¾ãģķ
    -0.09
    éĻIJå®ļ
    -0.08
     nợ
    -0.08
     Helsinki
    -0.08
    adox
    -0.08
    ote
    -0.08
    essor
    -0.08
    POSITIVE LOGITS
    人们对
    0.09
    ÙĪØ·
    0.09
    èģĮä¸ļæķĻèĤ²
    0.09
    建åįİ
    0.09
     Kah
    0.08
     calls
    0.08
    دÙĪ
    0.08
    ä¸ªåĽ½å®¶
    0.08
    ä¸ĢèĤ¡
    0.08
    dy
    0.08
    Activations Density 0.006%

    No Known Activations