© 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. 51303
    Prev
    Next
    INDEX
    Explanations

    names like Stefan, Damon, Simone, Elena

    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
    rd
    -0.10
    utsch
    -0.09
    pile
    -0.09
    Spo
    -0.09
    ä¿Ŀä½ı
    -0.09
    æĸĩåĮĸ交æµģ
    -0.09
    Spoiler
    -0.09
    оÑĢÑĤ
    -0.08
    ×Ļ×ij×ķת
    -0.08
    caster
    -0.08
    POSITIVE LOGITS
    ï¸ı
    0.09
    CHIP
    0.09
    uae
    0.09
    è¿ĻäºĽéĥ½æĺ¯
    0.09
    bole
    0.09
    resentation
    0.09
     unins
    0.08
    èĥ¤
    0.08
    å¿Ĺ强
    0.08
     ngá»Ļ
    0.08
    Activations Density 0.011%

    No Known Activations