© 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. 20687
    Prev
    Next
    INDEX
    Explanations

    names resembling "Levin", "Marvin", "Devin", "Amar"

    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
    ×ķת
    -0.09
    ä¸Ģå®ļçļĦ
    -0.09
    æĿª
    -0.09
    UME
    -0.09
     fines
    -0.08
    综
    -0.08
    mpeg
    -0.08
     Sheridan
    -0.08
     mẽ
    -0.08
    ÅĻ
    -0.08
    POSITIVE LOGITS
    ly
    0.14
    ivate
    0.10
    ienza
    0.10
    溽
    0.10
    ä¹İ
    0.09
    ../../../
    0.09
    nh
    0.09
    ../../
    0.09
    çĶ¨èĩªå·±çļĦ
    0.09
    饥
    0.09
    Activations Density 0.010%

    No Known Activations