© 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. 19486
    Prev
    Next
    INDEX
    Explanations

    prices ending in 9

    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
    ãģĤãĤĮ
    -0.09
    TERS
    -0.09
    ucha
    -0.08
     Wich
    -0.08
     hog
    -0.08
    Dou
    -0.08
    æľIJ
    -0.08
    失
    -0.08
    ç»ı纪人
    -0.08
    жд
    -0.08
    POSITIVE LOGITS
    笼
    0.10
    onas
    0.10
    å»ºåĽ½
    0.09
    éķ¿éķ¿
    0.09
    Solo
    0.09
    è¿ĺä¸įå¤Ł
    0.09
    解æĶ¾
    0.09
    ylon
    0.08
    èµĦ
    0.08
    ison
    0.08
    Activations Density 0.043%

    No Known Activations