© 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. 63288
    Prev
    Next
    INDEX
    Explanations

    takes time or quantity

    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
    导åIJij
    -0.09
    æĽ¦
    -0.09
    æľŁæľĽ
    -0.09
    åĩºåıij
    -0.09
    åĩºè¡Ģ
    -0.08
    asso
    -0.08
    inker
    -0.08
    æľīçĶ¨çļĦ
    -0.08
    éĩįä¸Ńä¹ĭéĩį
    -0.08
    å·®è·Ŀ
    -0.08
    POSITIVE LOGITS
    çIJĨ解åĴĮ
    0.10
    宿
    0.09
    èĢģé¾Ħ
    0.09
    åķĨä¸ļåĮĸ
    0.09
    ItemClick
    0.08
     slog
    0.08
    ä¸Ŀ
    0.08
    æīįèĥ½
    0.08
     Oliv
    0.08
    zan
    0.08
    Activations Density 0.032%

    No Known Activations