© 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. 7859
    Prev
    Next
    INDEX
    Explanations

    certainly above, this rate, this spread

    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
    æ¯Ķå¦Ĥ说
    -0.12
    èѬå¦Ĥ
    -0.10
    æģ°å¥½
    -0.09
    æĦİ
    -0.09
    æģ°æģ°
    -0.09
    é¦ĸåħĪæĺ¯
    -0.09
    é¾Į
    -0.09
    åĭ¾
    -0.09
    å¾Ģå¾Ģä¼ļ
    -0.09
    æĶ¹èī¯
    -0.09
    POSITIVE LOGITS
    åı¯æĥ³
    0.12
    åı¯æĥ³èĢĮçŁ¥
    0.11
    说æĺİ
    0.09
    足以
    0.09
    åŁºæķ°
    0.09
    åı¯è§ģ
    0.08
    çĶ±æѤåı¯è§ģ
    0.08
     Tas
    0.08
    æĴij
    0.08
    缸å½ĵäºİ
    0.08
    Activations Density 0.101%

    No Known Activations