© 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. 50725
    Prev
    Next
    INDEX
    Explanations

    comma followed by word

    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
    ãĤīãģı
    -0.11
    åĮĹ京åĨ¬å¥¥
    -0.10
    é¹Ĺ
    -0.10
    ä¸įçĦ¶
    -0.10
    altı
    -0.10
    æľ¬æĬ¥
    -0.09
    å®ĥ们
    -0.09
    anguard
    -0.09
    ãģĹãģ¾ãģĦ
    -0.09
    agan
    -0.09
    POSITIVE LOGITS
    çĶŁæ´»åľ¨
    0.09
    лиÑĤ
    0.07
     Heller
    0.07
    çļĦä¸ĸçķĮ
    0.07
    ÙĬÙĤ
    0.07
    è¿Ļä½į
    0.07
    è¿ĻåIJį
    0.06
    9
    0.06
    åİ®
    0.06
    sn
    0.06
    Activations Density 0.226%

    No Known Activations