© 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. 17987
    Prev
    Next
    INDEX
    Explanations

    cloud computing and services

    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
    滥
    -0.10
    éļľ
    -0.09
    ugs
    -0.09
    adel
    -0.09
    å«ī
    -0.09
    çıŃåŃIJ
    -0.09
    æ°ij主çĶŁæ´»
    -0.09
    è¦ģåģļ
    -0.09
    anut
    -0.09
    HOLDER
    -0.09
    POSITIVE LOGITS
    äºij端
    0.13
     cloud
    0.10
    两端
    0.10
    社ä¼ļåĮĸ
    0.09
    äºij
    0.09
    å¤ĸåĮħ
    0.09
    å§Ķæīĺ
    0.08
    pra
    0.08
    èĴ¸æ±½
    0.08
    äºij计ç®Ĺ
    0.08
    Activations Density 0.168%

    No Known Activations