© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50340
    Prev
    Next
    INDEX
    Explanations

    management or treatment

    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
    lingen
    -0.09
    æİ´
    -0.09
    åıijå±ķæł¼å±Ģ
    -0.09
    æĸ¹åľĨ
    -0.09
    产çĶŁçļĦ
    -0.08
    .dev
    -0.08
    orado
    -0.08
    ä¸Ģ大
    -0.08
    éģIJ
    -0.08
    립
    -0.08
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.12
    ä»įæĺ¯
    0.11
    èĢĮéĿŀ
    0.10
     simplement
    0.10
    åIJĦè¡Į
    0.09
    å¢ŀèµĦ
    0.09
    åī½
    0.09
     пÑĢоÑģÑĤо
    0.09
    .mods
    0.09
     simply
    0.09
    Activations Density 0.287%

    No Known Activations