© 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. 32916
    Prev
    Next
    INDEX
    Explanations

    shockwaves

    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
    æĺŁæĺŁ
    -0.09
    æ¡£
    -0.09
    åĸĭ
    -0.09
    åĥ»
    -0.09
    æīĵæĬĺ
    -0.09
    æī®
    -0.09
     Obs
    -0.09
    åģļå®Į
    -0.09
    ارد
    -0.08
    çĹĤ
    -0.08
    POSITIVE LOGITS
    æĥĬ讶
    0.19
    éľĩæĥĬ
    0.17
    æĥĬåı¹
    0.17
    éªĩ
    0.16
    æĥĬåĸľ
    0.16
    åIJĥæĥĬ
    0.16
    é©ļ
    0.15
    æĥĬ
    0.15
    æĦķ
    0.15
    æĥĬèī³
    0.14
    Activations Density 0.087%

    No Known Activations