© 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. 35135
    Prev
    Next
    INDEX
    Explanations

    news and industry sectors

    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
    ложен
    -0.11
    çIJ¢
    -0.09
    夸
    -0.09
    /manual
    -0.09
    è¯¥é¡¹çĽ®
    -0.08
    鸳
    -0.08
    .GetService
    -0.08
    æѤç§į
    -0.08
    æĤĶ
    -0.08
    è¾¾æłĩ
    -0.08
    POSITIVE LOGITS
    æľĢæĸ°
    0.11
    è¦ģéĹ»
    0.11
    åĨħå¹ķ
    0.11
    æ°ijçĶŁ
    0.09
    åIJĦæĸ¹éĿ¢
    0.09
     latest
    0.09
    缸åħ³åĨħ容
    0.09
    çĥŃçĤ¹
    0.08
    åŬ
    0.08
    è¿Ľç¨ĭ
    0.08
    Activations Density 0.211%

    No Known Activations