© 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. 23326
    Prev
    Next
    INDEX
    Explanations

    changes and shifts

    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
    éĢļå¾Ģ
    -0.10
    é¦Ĵ头
    -0.09
    æĥĭ
    -0.09
    çĦ°
    -0.09
    éļ¾
    -0.09
    alem
    -0.09
    à¹Ģà¸īà¸ŀาะ
    -0.09
    à¸Ńร
    -0.09
    æ¦ľé¦ĸ
    -0.09
    éĻ·åħ¥äºĨ
    -0.09
    POSITIVE LOGITS
    åıĺåĮĸ
    0.31
    çļĦåıĺåĮĸ
    0.28
     changes
    0.28
     change
    0.26
    è®ĬåĮĸ
    0.25
    åıĺéĿ©
    0.23
    åıĺæĽ´
    0.22
    æĶ¹åıĺ
    0.22
     Changes
    0.22
    changes
    0.21
    Activations Density 0.569%

    No Known Activations