© 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. 55399
    Prev
    Next
    INDEX
    Explanations

    hotels

    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
    åħ®
    -0.11
    enant
    -0.10
    zelf
    -0.10
    家ä¼Ļ
    -0.10
    -pocket
    -0.09
     draining
    -0.09
    íĭ°
    -0.09
    Õ¿
    -0.08
     unt
    -0.08
    è·Į
    -0.08
    POSITIVE LOGITS
    ulous
    0.09
    ç¥Ī祷
    0.09
    æĸĩåĮĸèĬĤ
    0.09
    vard
    0.09
    éĺ´éĺ³
    0.09
    åĭĸ
    0.09
    æĿijæ°ij们
    0.09
     vil
    0.08
    æľ¬äºº
    0.08
     narr
    0.08
    Activations Density 0.006%

    No Known Activations