© 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. 37791
    Prev
    Next
    INDEX
    Explanations

    comparison; different; various

    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
    xBC
    -0.10
     Bucc
    -0.10
    çĶ¨æĪ·æıIJä¾Ľ
    -0.10
    åºĻ
    -0.09
     táºŃn
    -0.09
    -tags
    -0.09
    æĪİ
    -0.09
    IAS
    -0.09
    åħ·æľīèī¯å¥½
    -0.08
    è¿Ļæī¹
    -0.08
    POSITIVE LOGITS
    ä¸Ģè§Ī
    0.11
    示æĦı
    0.11
    ä¸įåIJĮçļĦ
    0.11
     different
    0.11
    ä¸įåIJĮ
    0.10
     various
    0.10
    åIJĦç§į
    0.10
    3
    0.09
    åıĺè¿ģ
    0.09
    åħ³ç³»
    0.09
    Activations Density 0.165%

    No Known Activations