© 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. 55557
    Prev
    Next
    INDEX
    Explanations

    company names and suffixes

    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
    æĪ¿ä¸ľ
    -0.09
    éĺ¿æ£®
    -0.08
    æѤ类
    -0.08
    thane
    -0.08
    大æĸ¹
    -0.08
    åĮ»ç§ij大åѦ
    -0.08
    tü
    -0.08
    æ²³æµģåŁŁ
    -0.08
    æĦ«
    -0.08
     phúc
    -0.07
    POSITIVE LOGITS
    åıĬåħ¶
    0.10
    /about
    0.09
    /of
    0.08
     اÙĦÙħص
    0.08
    çĴ¨
    0.08
    utes
    0.08
    ä¸ĭä¸ĢæŃ¥
    0.08
    å®ŀæĸ½ç»ĨåĪĻ
    0.08
    educt
    0.08
    çı²
    0.08
    Activations Density 0.762%

    No Known Activations