© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37394
    Prev
    Next
    INDEX
    Explanations

    procedures, policies, protocols

    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
    ç¥ī
    -0.11
    æĮĩæĮ¥éĥ¨
    -0.09
    åĵij
    -0.09
    åİĿ
    -0.09
     Jack
    -0.09
    éĶħ
    -0.09
    鸳
    -0.09
    ÇĴ
    -0.08
     jack
    -0.08
    .bulk
    -0.08
    POSITIVE LOGITS
     procedures
    0.16
    æµģç¨ĭ
    0.16
     procedure
    0.15
     пÑĢоÑĨед
    0.13
     Procedures
    0.12
    Procedure
    0.12
    procedure
    0.12
    è§Ħå®ļ
    0.11
    è§ĦèĮĥ
    0.11
     protocols
    0.11
    Activations Density 0.101%

    No Known Activations