© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52188
    Prev
    Next
    INDEX
    Explanations

    found or find

    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
    å¼¹
    -0.09
    æ¯ıä¸Ģ个人
    -0.09
     Reid
    -0.09
    åĪĪ
    -0.09
    ä»ħ次äºİ
    -0.08
    ä»ħ次
    -0.08
     Sprint
    -0.08
     Suff
    -0.08
    (pf
    -0.08
    åIJ¬å¾Ĺ
    -0.08
    POSITIVE LOGITS
    æī¾åĪ°äºĨ
    0.23
    æī¾åĪ°
    0.19
    åıijçİ°äºĨ
    0.16
     gefunden
    0.13
    æī¾äºĨ
    0.13
     ì°¾
    0.13
     найд
    0.12
    寻
    0.12
     finding
    0.12
    åIJĪéĢĤ
    0.12
    Activations Density 0.152%

    No Known Activations