© 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. 35173
    Prev
    Next
    INDEX
    Explanations

    fortunate, lucky, privileged, blessed, pleasure

    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
    ä¸įå®ļ
    -0.09
    abal
    -0.09
    å²Ĺ
    -0.09
    主åĬ¨æĢ§
    -0.09
    æīĭä¸ŃçļĦ
    -0.08
    åľ°ä¸ĭ
    -0.08
    ä¸įåı¯
    -0.08
    éģĵçIJĨ
    -0.08
    åıijæī¬
    -0.08
    èijº
    -0.08
    POSITIVE LOGITS
    å¿Ŀ
    0.10
    çĪ±ä¸Ĭ
    0.10
    ior
    0.10
    æ²Ľ
    0.10
    幸è¿IJ
    0.10
    çŁ¥éģĵèĩªå·±
    0.09
    ä¸įå±ŀäºİ
    0.09
    ä¸į幸
    0.09
    éģĩä¸Ĭ
    0.09
    大家éĥ½åľ¨
    0.09
    Activations Density 0.051%

    No Known Activations