© 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. 50674
    Prev
    Next
    INDEX
    Explanations

    Gothic architecture and style

    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
    åľĥ
    -0.10
    maids
    -0.09
    身边çļĦ
    -0.09
    lessly
    -0.09
    è¹Ī
    -0.09
    estre
    -0.09
    iese
    -0.09
    å·²ä¹ħçļĦ
    -0.09
    æŀŀ
    -0.08
    ãģĹãģ¾ãģĨ
    -0.08
    POSITIVE LOGITS
    ized
    0.10
    icism
    0.09
    berger
    0.09
    pus
    0.09
    icity
    0.09
    åĽłä¸ºä»ĸ们
    0.08
    mü
    0.08
    engl
    0.08
    agli
    0.08
     Mig
    0.08
    Activations Density 0.025%

    No Known Activations