© 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. 50050
    Prev
    Next
    INDEX
    Explanations

    peroxisome proliferator-activated receptor

    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
    æīĭå¥Ĺ
    -0.09
    _DS
    -0.09
    ucus
    -0.08
    缴åįĩæľº
    -0.08
    _TM
    -0.08
     Silicone
    -0.08
    .rf
    -0.08
     bloodstream
    -0.08
    ewise
    -0.08
    è¿ĩæķı
    -0.08
    POSITIVE LOGITS
    磫æŃ£
    0.10
    ä¸Ĭè°ĥ
    0.10
    à´´
    0.09
    åIJ¬è¯¾
    0.09
    è¾Ĩ
    0.09
    磫
    0.09
     poverty
    0.08
    èĤ¥èĥĸ
    0.08
    æī¶è´«
    0.08
    é»Ħéĩij
    0.08
    Activations Density 0.507%

    No Known Activations