© 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. 57672
    Prev
    Next
    INDEX
    Explanations

    greetings and thanks

    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
    éĶ»éĢł
    -0.10
    æļĸ
    -0.10
    çįIJ
    -0.09
     Ey
    -0.09
    èĩ´æķ¬
    -0.09
    æĦŁè°¢
    -0.09
     Ø´Ùĥرا
    -0.09
    åĨįè§ģ
    -0.09
    饯
    -0.08
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.08
    POSITIVE LOGITS
    æį¢
    0.10
    èĤ¥
    0.09
    åĿİåĿ·
    0.09
     бÑİ
    0.08
    æıĽ
    0.08
    rous
    0.08
    ulk
    0.08
     ÐĵÑĢ
    0.08
    ä»Ģä¹Īåı«
    0.08
    arna
    0.07
    Activations Density 0.037%

    No Known Activations