© 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. 22829
    Prev
    Next
    INDEX
    Explanations

    family relationships or home context

    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
    ä¸Ģ带
    -0.10
    èĥĨ
    -0.09
    çģ¾
    -0.09
    /Foundation
    -0.09
    è¹ĩ
    -0.09
    å¸ĸåŃIJ
    -0.08
    åıĶ
    -0.08
    Ë®
    -0.08
    è¿Ļæł·æīįèĥ½
    -0.08
    à¹Ĥà¸ķ
    -0.08
    POSITIVE LOGITS
    emann
    0.10
    ä¸įèĪį
    0.09
    oran
    0.09
    abay
    0.09
    æĥłæ°ij
    0.09
    ä½ĵçİ°åľ¨
    0.09
    EGA
    0.09
    éĿ¢åħ·
    0.08
    MAND
    0.08
     Tes
    0.08
    Activations Density 0.007%

    No Known Activations