© 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. 27752
    Prev
    Next
    INDEX
    Explanations

    ease of use or manipulation

    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
    éŀį
    -0.10
    æŀ¯
    -0.09
    ä¸İåIJ¦
    -0.09
    è´«
    -0.09
     Reign
    -0.09
    åĽŀå½Ĵ
    -0.09
    çĥ¹
    -0.08
    å¯Ĥ
    -0.08
     Opport
    -0.08
    çĤĴèĤ¡
    -0.08
    POSITIVE LOGITS
    åĽ°éļ¾
    0.11
    æĪIJåĬŁçİĩ
    0.10
    çĶ¨æīĭ
    0.10
    æģ¼
    0.10
    çĶ¨åĬĽ
    0.10
    äºĨåįĬ天
    0.10
     assistance
    0.10
    解å¼Ģ
    0.09
    tempts
    0.09
    æ¦ľ
    0.09
    Activations Density 0.153%

    No Known Activations