© 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. 10378
    Prev
    Next
    INDEX
    Explanations

    new followed by a noun

    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
    éĤ£æł·çļĦ
    -0.09
    ä¿Ŀé²ľ
    -0.09
    åĪ®
    -0.09
    ä¸Ģ代
    -0.09
    çħĮ
    -0.09
    æİĮ声
    -0.09
    ForResult
    -0.09
    æĥ³ä¸įåĪ°
    -0.09
    RIA
    -0.08
    åĴĨ
    -0.08
    POSITIVE LOGITS
     newfound
    0.11
    éŀį
    0.10
    æĸ°ãģĹãģĦ
    0.10
    æĸ°çļĦ
    0.09
    illi
    0.09
     новÑĭй
    0.09
    éĤij
    0.09
    ãģªãģĦãĤĪãģĨãģ«
    0.09
    çĽ
    0.09
     new
    0.09
    Activations Density 0.029%

    No Known Activations