© 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. 37378
    Prev
    Next
    INDEX
    Explanations

    reliability and dependability

    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
    RAL
    -0.10
    lify
    -0.10
     Vander
    -0.09
    æĶ¶è´¹æłĩåĩĨ
    -0.08
    å¯Į
    -0.08
    ä½ķåĨµ
    -0.08
    chers
    -0.08
    INA
    -0.08
    еÑĢ
    -0.08
    åĻĮ
    -0.08
    POSITIVE LOGITS
    èµ·æĿ¥
    0.10
    åŀķ
    0.09
    inkle
    0.09
    人éĥ½
    0.09
    ноÑģÑĤÑĮÑİ
    0.09
    åľºåĿĩ
    0.08
    ately
    0.08
    ENA
    0.08
    spe
    0.08
    æĮĿ
    0.08
    Activations Density 0.015%

    No Known Activations