© 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. 21124
    Prev
    Next
    INDEX
    Explanations

    I wish I could

    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
    åİ¢
    -0.09
    ä¹Łåı¯ä»¥
    -0.08
    å¿ĥèĦıçĹħ
    -0.08
     Schn
    -0.08
    è¿ĺåı¯ä»¥
    -0.08
    ä»ĸæĽ¾
    -0.08
    ä¹ĭè·¯
    -0.08
    åı¯èĥ½åĩºçİ°
    -0.08
    itet
    -0.08
     might
    -0.08
    POSITIVE LOGITS
    ÙģÙĪ
    0.11
    bread
    0.10
    azzi
    0.10
    elor
    0.10
    eneg
    0.09
    è§ģåĪ°
    0.09
    éľı
    0.09
    prise
    0.09
    ä¸Ģä¸Ģ
    0.09
    éĤ¦
    0.09
    Activations Density 0.017%

    No Known Activations