© 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. 56960
    Prev
    Next
    INDEX
    Explanations

    combines or blends elements

    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
     ÑĤоже
    -0.11
    èį¡
    -0.11
    åıªè¦ģæĺ¯
    -0.09
    第äºĮæī¹
    -0.09
    饽
    -0.09
    å¦ĤæĦı
    -0.09
    æĤĦæĤĦ
    -0.08
     Gesture
    -0.08
    èį¯ä¸ļ
    -0.08
    çĶ»åį·
    -0.08
    POSITIVE LOGITS
    åľ¨ä¸Ģèµ·
    0.11
    æĬĢæľ¯åĴĮ
    0.11
    é«ĺ强度
    0.09
    _elt
    0.09
    çĤ½
    0.09
    æŀģ大
    0.09
    欸
    0.08
    èµĦæºIJä¼ĺåĬ¿
    0.08
     together
    0.08
    äºĮèĢħ
    0.08
    Activations Density 0.099%

    No Known Activations