© 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. 5589
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    ä½ľä¸ºä¸Ģ个
    -0.10
    åıªæĺ¯ä¸Ģ个
    -0.09
    ather
    -0.09
     từng
    -0.09
    zelf
    -0.09
    ä¸Ģç³»åĪĹ
    -0.09
    ä»Ģä¹ĪæĦıæĢĿ
    -0.08
    çĻ»åľº
    -0.08
    .CommandType
    -0.08
    åĨħ容ç®Ģä»ĭ
    -0.08
    POSITIVE LOGITS
    åĢ¼å¾Ĺ注æĦı
    0.10
    lit
    0.09
    åIJ»
    0.09
    æĬ¥ç¤¾
    0.08
     Shelby
    0.08
    ÑĥÑĪ
    0.08
    åºĶ注æĦı
    0.08
    è¦ģ注æĦı
    0.08
    onta
    0.08
     опÑĭÑĤ
    0.08
    Activations Density 0.042%

    No Known Activations