© 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. 11214
    Prev
    Next
    INDEX
    Explanations

    urine, piss, spit, strict

    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
    lash
    -0.12
     возд
    -0.09
    解æĶ¾æĢĿæĥ³
    -0.09
    æħ
    -0.09
    æīĵå¾Ĺ
    -0.09
    oes
    -0.08
    空åīį
    -0.08
     Loving
    -0.08
    oot
    -0.08
     unre
    -0.08
    POSITIVE LOGITS
    ening
    0.10
    马桶
    0.10
    æİīäºĨ
    0.09
    imest
    0.09
    /rfc
    0.09
    rica
    0.09
    esting
    0.08
    _frontend
    0.08
    æ³ļ
    0.08
    eners
    0.08
    Activations Density 0.007%

    No Known Activations