© 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. 22651
    Prev
    Next
    INDEX
    Explanations

    bathroom and shower spaces

    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
    ivist
    -0.10
    rous
    -0.09
    åĴĮå®ĮåĸĦ
    -0.09
    è¾ĥ强çļĦ
    -0.09
    ä¸įæĪIJ
    -0.09
    oman
    -0.09
    anna
    -0.09
     lá»ĩ
    -0.09
    è¾ĥ大çļĦ
    -0.09
    éĩįè¦ģæĦıä¹ī
    -0.08
    POSITIVE LOGITS
    anson
    0.09
    çĿ¬
    0.09
    åīįèĢħ
    0.09
    jin
    0.08
    æħĿ
    0.08
    éĩĮçļĦ
    0.08
     stall
    0.08
    enticate
    0.08
    elu
    0.08
    اÙħÙĦ
    0.08
    Activations Density 0.006%

    No Known Activations