© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52537
    Prev
    Next
    INDEX
    Explanations

    full-

    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
    æ´ģåĩĢ
    -0.09
     Authorities
    -0.09
     Ale
    -0.08
     Freed
    -0.08
    UDGE
    -0.08
    çıįçıł
    -0.08
    æīĢå¾Ĺ
    -0.08
    竹
    -0.08
    æµģåĬ¨æĢ§
    -0.08
    å¿ĥ仪çļĦ
    -0.08
    POSITIVE LOGITS
    /full
    0.10
    åĸı
    0.10
     سبÙĬÙĦ
    0.09
    éĻª
    0.09
    ement
    0.09
    ools
    0.09
    éĤ£ä¹Ī容æĺĵ
    0.09
    way
    0.08
    ToOne
    0.08
    olta
    0.08
    Activations Density 0.054%

    No Known Activations