© 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. 57815
    Prev
    Next
    INDEX
    Explanations

    news, books, media, articles

    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
    è¾ĩ
    -0.09
    Called
    -0.09
    ä¿Ŀåį«
    -0.09
    åł¡
    -0.08
    æĿĤå¿Ĺ社
    -0.08
    è£ĺ
    -0.08
    æĥķ
    -0.08
    纪å§Ķ
    -0.08
    chia
    -0.08
    Ñĥб
    -0.08
    POSITIVE LOGITS
    urally
    0.10
    å®ŀéĻħè¡ĮåĬ¨
    0.10
    Arena
    0.09
    çĺ°
    0.09
    å¤ļç§įå½¢å¼ı
    0.09
     scm
    0.09
    éĽªèĬ±
    0.09
     ÑĦоÑĢме
    0.09
    assin
    0.09
    åŃĢ
    0.08
    Activations Density 0.190%

    No Known Activations