© 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. 3994
    Prev
    Next
    INDEX
    Explanations

    local government areas and administrations

    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
     pul
    -0.09
    éļĶéŁ³
    -0.09
    éļ§
    -0.09
    å°±è¿Ļä¹Ī
    -0.08
    å°Ĩ士
    -0.08
    phen
    -0.08
    驯
    -0.08
    lius
    -0.08
    奢
    -0.08
    æĬ«
    -0.08
    POSITIVE LOGITS
     Disqus
    0.10
    nex
    0.09
    ä¸Ģç»Ħ
    0.09
    责任åĪ¶
    0.09
     AIS
    0.09
     окÑĢÑĥг
    0.09
    åħ³éŨ
    0.09
    åij¨è¾¹
    0.09
    ä¸Ģä½ĵåĮĸ
    0.09
    ivi
    0.09
    Activations Density 0.230%

    No Known Activations