© 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. 50887
    Prev
    Next
    INDEX
    Explanations

    processing, storage, computer, corporation

    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
    ç»·
    -0.10
    éŀĺ
    -0.09
    æļ´
    -0.09
    åģļä¸Ģ个
    -0.09
    #ac
    -0.09
    产ä¸ļåįĩ级
    -0.09
    caff
    -0.09
    å³°
    -0.09
    马路
    -0.08
    æĬĹåĩ»
    -0.08
    POSITIVE LOGITS
    èĮĥ
    0.10
     IBM
    0.10
    IBM
    0.09
    æľºæ¢°åĮĸ
    0.09
    åıĪ好
    0.09
    èĥĮæĻ¯
    0.09
     pant
    0.09
    flen
    0.08
    计ç®Ĺæľº
    0.08
    å¯Ħ
    0.08
    Activations Density 0.146%

    No Known Activations