© 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. 18228
    Prev
    Next
    INDEX
    Explanations

    ingredients or cooking instructions

    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
    åįĥéĩĮ
    -0.10
    æıĦ
    -0.10
    åĩºåĬ¨
    -0.09
     bÃło
    -0.09
    æĸĻ
    -0.09
    åıĺ身
    -0.09
    esus
    -0.09
    ATO
    -0.09
    æ®ĭçķĻ
    -0.09
    äºĮ次
    -0.09
    POSITIVE LOGITS
    æĹħéĢĶ
    0.09
    å°ijéĩı
    0.08
    æĦŁåħ´è¶£çļĦ
    0.08
    计
    0.08
    éŁ
    0.08
    oggles
    0.07
    å®ļäºĨ
    0.07
    retry
    0.07
    å°ij许
    0.07
    ä¸Ģèµ·åİ»
    0.07
    Activations Density 0.004%

    No Known Activations