© 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. 18272
    Prev
    Next
    INDEX
    Explanations

    much looking forward

    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
    emu
    -0.08
    客è§Ĥ
    -0.08
     JL
    -0.08
    rede
    -0.08
    ((&
    -0.08
    _SCOPE
    -0.08
    æIJŀ
    -0.08
    å¾Īéĩįè¦ģçļĦ
    -0.08
    ALE
    -0.07
    oplan
    -0.07
    POSITIVE LOGITS
    æĺ¯ä¸Ģ件
    0.11
    ä¿ĿæĮģçĿĢ
    0.11
     пÑĢеж
    0.10
    ä¸Ģ个èģĮä¸ļ
    0.10
    åľ¨äºİ
    0.10
    第äºĮç§į
    0.09
    æĺ¯ä¸Ģ座
    0.09
    主ä½ĵ责任
    0.09
    ä»¥äººä¸ºæľ¬
    0.09
    олÑĮ
    0.09
    Activations Density 0.016%

    No Known Activations