© 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. 56941
    Prev
    Next
    INDEX
    Explanations

    charitable organizations or fundraising

    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
    麻
    -0.09
    istes
    -0.09
    ascal
    -0.08
    æ¡Į
    -0.08
    .setHeader
    -0.08
    idad
    -0.08
    讫
    -0.08
    èĮ§
    -0.08
    å½Ĵ
    -0.08
    اصر
    -0.08
    POSITIVE LOGITS
    人家
    0.11
    ObjectContext
    0.10
    åľ¨åħ¨åĽ½
    0.09
    æł·
    0.09
    æł·çļĦ
    0.09
    VENT
    0.09
    chal
    0.09
    æĬķèµĦåŁºéĩij
    0.09
    otle
    0.09
    éĥ½ä¸įèĥ½
    0.09
    Activations Density 0.010%

    No Known Activations