© 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. 36446
    Prev
    Next
    INDEX
    Explanations

    Memphis locations

    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
    EUR
    -0.11
    æıĸ
    -0.10
    ä¸Ģ大åłĨ
    -0.09
    ç²½
    -0.09
    acha
    -0.09
    è¾Ħ
    -0.09
    erve
    -0.09
    ummy
    -0.08
    帽
    -0.08
    eur
    -0.08
    POSITIVE LOGITS
    ä¸įä¸Ĭ
    0.10
    outs
    0.09
    viz
    0.08
    åı£æ°Ķ
    0.08
     outs
    0.08
    atform
    0.08
    è¦ģæĬĬ
    0.08
    yll
    0.08
     trailing
    0.08
    ceso
    0.08
    Activations Density 0.004%

    No Known Activations