© 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. 51002
    Prev
    Next
    INDEX
    Explanations

    ARIA Award, guidelines

    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
    人éĢī
    -0.10
    èµį
    -0.09
    inner
    -0.09
    詹
    -0.09
    好人
    -0.09
    æĹłäºº
    -0.09
    .Peek
    -0.09
    ãģĹãģ¾ãģĨ
    -0.09
    çķĻæĦı
    -0.09
    çļĦç«ŀäºī
    -0.08
    POSITIVE LOGITS
    zing
    0.09
    EGIN
    0.09
    UBL
    0.08
    ضا
    0.08
    icult
    0.08
     chances
    0.08
    esz
    0.08
    oire
    0.08
    icle
    0.08
    ely
    0.08
    Activations Density 0.025%

    No Known Activations