© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52749
    Prev
    Next
    INDEX
    Explanations

    mac address

    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
    æ³ķå®ļ
    -0.12
    ãĥķãĤ©ãĥ¼
    -0.10
    è¤Ĵ
    -0.09
    å½·
    -0.09
    å°±æĺ¯ä¸ºäºĨ
    -0.08
    CDATA
    -0.08
    è°Ĩ
    -0.08
     Bak
    -0.08
    ç¨Ĺ
    -0.08
    ÑĨин
    -0.08
    POSITIVE LOGITS
    ä¸ŃåĽ½æĸĩåĮĸ
    0.09
    çķ´
    0.08
     Lif
    0.08
    åľ°å¤Ħ
    0.08
    ä¹ħ
    0.08
     Incorporated
    0.08
     sph
    0.08
    rine
    0.08
    鼬
    0.08
    ses
    0.07
    Activations Density 0.025%

    No Known Activations