© 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. 34774
    Prev
    Next
    INDEX
    Explanations

    Malala Yousafzai or Gallup transactions

    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
    åĦ¿
    -0.08
    éĻĶ
    -0.08
     Telegraph
    -0.08
    代åĬŀ
    -0.08
    esk
    -0.08
    omer
    -0.08
     Caller
    -0.08
    æĭ¬
    -0.08
    inh
    -0.07
    æ½Ń
    -0.07
    POSITIVE LOGITS
    头æĻķ
    0.10
    ä½Ĩä¸įéĻIJ
    0.10
     cüm
    0.10
    pearance
    0.10
    ä¸įæŃ¢
    0.10
    lasses
    0.09
    å·´èı²
    0.09
    åıĭæĥħéĵ¾æİ¥
    0.09
    ê¹Ģ
    0.09
    èľĤ
    0.09
    Activations Density 0.003%

    No Known Activations