© 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. 39144
    Prev
    Next
    INDEX
    Explanations

    nominal control, Eastern bloc, influence is

    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
    åĬŀ好
    -0.10
    æĥķ
    -0.10
    åī§
    -0.09
    atat
    -0.09
    LES
    -0.09
    çħ²
    -0.09
    纯åĩĢ
    -0.08
    å»ĭ
    -0.08
    éĤ£ä½į
    -0.08
    海峡
    -0.08
    POSITIVE LOGITS
    éĻĦå±ŀ
    0.10
    izard
    0.10
    æĮĩ导ä¸ĭ
    0.09
    æĮĩå°İ
    0.09
     countries
    0.09
    é¢Ĩ
    0.09
    æ³Ĭ
    0.09
    æĮĩ导
    0.09
    屬
    0.09
    æ·¤
    0.09
    Activations Density 0.045%

    No Known Activations