© 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. 53640
    Prev
    Next
    INDEX
    Explanations

    swimming pool

    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
    ì°½
    -0.10
    Boost
    -0.09
    _bootstrap
    -0.09
     sock
    -0.09
    æīĵåĩ»
    -0.09
    bootstrap
    -0.09
    -bootstrap
    -0.09
     bootstrap
    -0.09
    éĶ¤
    -0.09
    æįĨ
    -0.09
    POSITIVE LOGITS
    æ³³
    0.17
    游泳
    0.16
     swimming
    0.16
     pool
    0.15
    pool
    0.15
     pools
    0.13
    .pool
    0.13
     swim
    0.13
    Pool
    0.13
     Swimming
    0.13
    Activations Density 0.094%

    No Known Activations