© 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. 62388
    Prev
    Next
    INDEX
    Explanations

    contrast introduction

    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
    åĨĻçĿĢ
    -0.10
    åij¸
    -0.09
    ullo
    -0.09
    åħ¶å®ŀå°±æĺ¯
    -0.09
    亲çĪ±çļĦ
    -0.08
    çĶļèĩ³è¿ŀ
    -0.08
    oud
    -0.08
    -0.08
    çĪ±åĽ½ä¸»ä¹ī
    -0.08
    åı¹
    -0.08
    POSITIVE LOGITS
     unlike
    0.13
    Unlike
    0.12
     Unlike
    0.11
    以å¾Ģ
    0.11
    ä¸įåĥı
    0.11
    ä¸Ĭ次
    0.10
    SOR
    0.10
    寻常
    0.10
    ably
    0.09
    ä»»ä½ķæŶåĢĻ
    0.09
    Activations Density 0.017%

    No Known Activations