© 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. 10757
    Prev
    Next
    INDEX
    Explanations

    real estate agent, broker, MLS

    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
    æİ¥è¿ĩ
    -0.09
    itan
    -0.08
    ä¸Ģè§Ĵ
    -0.08
    ä¸įç»ı
    -0.08
    åħ«å¹´
    -0.08
    æį
    -0.08
    è¿IJèIJ¥ç®¡çIJĨ
    -0.08
    OF
    -0.08
    çĮ¿
    -0.08
    çĩ®
    -0.08
    POSITIVE LOGITS
    两级
    0.10
    çī©ä¸ļ
    0.09
    Ñĥж
    0.09
    plen
    0.09
    æĪ¿äº§
    0.08
    _subscribe
    0.08
    åŃIJå¼¹
    0.08
     Sidney
    0.08
    uffy
    0.08
    æѧ
    0.08
    Activations Density 0.015%

    No Known Activations