© 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. 9081
    Prev
    Next
    INDEX
    Explanations

    no, a, an

    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
    Svc
    -0.10
    åıªè¦ģæĺ¯
    -0.09
    ailed
    -0.08
    çĩ§
    -0.08
    èĢ·
    -0.08
    unner
    -0.08
    对æѤ
    -0.08
     Erg
    -0.08
    æ¼Ĥæµģ
    -0.08
     pol
    -0.08
    POSITIVE LOGITS
     emphasis
    0.10
    æĬĦ
    0.09
    æİĴ
    0.09
    å¾Ī
    0.09
    åijķ
    0.09
    hé
    0.09
    vero
    0.09
    ä¼ļåıijçĶŁ
    0.08
    copies
    0.08
    é¢Ŀå¤ĸ
    0.08
    Activations Density 0.473%

    No Known Activations