© 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. 10949
    Prev
    Next
    INDEX
    Explanations

    storage rental units

    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
    åģķ
    -0.09
    å±ģèĤ¡
    -0.09
     plut
    -0.08
    åĤ¨å¤ĩ
    -0.08
    åħ¬è¯ī
    -0.08
    éĺµå®¹
    -0.08
    æŃ£ç¡®çļĦ
    -0.08
    åľ¨æĪijçľĭæĿ¥
    -0.08
    åĸĭ
    -0.08
    赡
    -0.08
    POSITIVE LOGITS
    裹
    0.09
    ç²Ĺç³Ļ
    0.09
    åıijå±ķ空éĹ´
    0.09
    ä¸Ģ段
    0.09
    æIJŃä¹ĺ
    0.09
    лиÑĨ
    0.09
     Bach
    0.09
    æ£ł
    0.08
    FileStream
    0.08
    lÃŃ
    0.08
    Activations Density 0.007%

    No Known Activations