© 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. 53534
    Prev
    Next
    INDEX
    Explanations

    need or lack

    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
    çļĦéģĵè·¯
    -0.11
    ä¸Ģ举
    -0.09
    chluss
    -0.09
    åĮħ袱
    -0.09
    deer
    -0.09
    deen
    -0.09
    æħİ
    -0.09
    eacher
    -0.09
    é£İåIJ¹
    -0.09
    å³Ļ
    -0.09
    POSITIVE LOGITS
    å¸ĤåľºçļĦ
    0.11
    å¸Ĥåľºä¸Ĭ
    0.10
    å¸Ĥåľº
    0.10
    çĹĽçĤ¹
    0.10
     market
    0.09
    å¸ĤåľºéľĢæ±Ĥ
    0.09
     missing
    0.09
     pent
    0.09
    è¿«åĪĩ
    0.09
    åĪļéľĢ
    0.09
    Activations Density 0.207%

    No Known Activations