© 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. 31112
    Prev
    Next
    INDEX
    Explanations

    Nouns followed by common contexts or suffixes

    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
    çīĪæĿĥæīĢæľī
    -0.10
    æķ´é¡¿
    -0.10
    å¾Ĺ天
    -0.10
    åłª
    -0.10
    ä¸Ģ群人
    -0.09
    æī¿
    -0.09
    éĤ£ä¸Ģ
    -0.09
    æİĮ
    -0.09
    缴å±ŀ
    -0.09
    èĥ¯
    -0.09
    POSITIVE LOGITS
    们
    0.18
    们çļĦ
    0.16
    åĢij
    0.15
    们éĥ½
    0.14
    sto
    0.09
    hood
    0.09
     Ach
    0.09
    å¾Ĥ
    0.09
    lets
    0.09
    innen
    0.09
    Activations Density 0.021%

    No Known Activations