© 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. 55792
    Prev
    Next
    INDEX
    Explanations

    license / agreement / provided

    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
    çĤ¹è¯Ħ
    -0.10
     Organic
    -0.08
    ocr
    -0.08
    åıĹ欢è¿İ
    -0.08
    osing
    -0.08
    åĪĽå§ĭ人
    -0.08
     organic
    -0.08
     Resume
    -0.08
    éĢıæĺİ
    -0.07
    åŃ¦ä¹łæĪIJ绩
    -0.07
    POSITIVE LOGITS
    å¯ĵ
    0.09
    æĥłåıĬ
    0.09
    é¦Ĩ
    0.09
    Ñĥма
    0.09
    retch
    0.09
     اÙĦÙĨÙģ
    0.09
    åŀĵ
    0.08
    éĩįå·¥
    0.08
    ä¹°çļĦ
    0.08
    anford
    0.08
    Activations Density 0.084%

    No Known Activations