© 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. 52372
    Prev
    Next
    INDEX
    Explanations

    understand why

    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
    uron
    -0.10
    ALT
    -0.09
    hd
    -0.09
    饥饿
    -0.09
    ãģķãģĦ
    -0.09
    念
    -0.09
    ä¸Ģè´¯
    -0.09
    سÙĬ
    -0.09
    æŃ»äº¡
    -0.08
    á»ĥn
    -0.08
    POSITIVE LOGITS
    为ä»Ģä¹Īä¼ļ
    0.13
    åĢ¾
    0.11
    åIJĪçIJĨæĢ§
    0.10
     understandable
    0.10
    åĤ¾
    0.10
    why
    0.10
    主è¦ģåİŁåĽł
    0.10
    å¸®ä½ł
    0.10
    帮ä»ĸ
    0.09
    åŁĶ
    0.09
    Activations Density 0.056%

    No Known Activations