© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50453
    Prev
    Next
    INDEX
    Explanations

    Wal-Mart, stores, brands

    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
    æĦı大
    -0.11
    åĪ¶èį¯
    -0.09
    èĻ»
    -0.09
    rades
    -0.09
    ãĤ«ãĥ©
    -0.09
    åħįç¨İ
    -0.09
    æĿĤå¿Ĺ社
    -0.08
    inery
    -0.08
    Binder
    -0.08
    鼶åĶ®åķĨ
    -0.08
    POSITIVE LOGITS
     poo
    0.10
    åĽŃæŀĹ
    0.09
    嬴
    0.09
    .shadow
    0.09
    åı¬åĶ¤
    0.09
    æĤ²åĵĢ
    0.09
    åijĺå·¥
    0.08
    æİĮ
    0.08
    æ·³
    0.08
    çĹĶ
    0.08
    Activations Density 0.059%

    No Known Activations