© 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. 10563
    Prev
    Next
    INDEX
    Explanations

    purpose of this study

    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
    ä½Ĩå®ĥ
    -0.10
    èĩªèº«çļĦ
    -0.09
    æīĢåľ¨çļĦ
    -0.08
    解åĨ³éĹ®é¢ĺ
    -0.08
    åľ¨æĦı
    -0.08
    èĪį
    -0.07
    åħ·ä½ĵæĥħåĨµ
    -0.07
    (CG
    -0.07
    ieve
    -0.07
    loom
    -0.07
    POSITIVE LOGITS
     this
    0.23
     nÃły
    0.22
     ÙĩØ°Ùĩ
    0.20
    è¿Ļä¸Ģ
    0.19
    this
    0.19
    éĢĻåĢĭ
    0.19
     ÑįÑĤом
    0.18
    è¿ĻäºĽ
    0.18
     Ùĩذا
    0.18
    è¿Ļ个
    0.18
    Activations Density 0.515%

    No Known Activations