© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36691
    Prev
    Next
    INDEX
    Explanations

    information: response, physical, requires, using, dent, use

    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
    edar
    -0.09
    zia
    -0.08
    akin
    -0.08
    aking
    -0.08
     diplomatic
    -0.08
    æŃ£èĥ½éĩı
    -0.08
    æĪ¿
    -0.08
    åľ°æ¯¯
    -0.08
    å¼Ģåıij
    -0.08
    ãģļ
    -0.07
    POSITIVE LOGITS
    çļĦè®¤çŁ¥
    0.12
    åĵģçīĮçļĦ
    0.11
    æĦŁçŁ¥
    0.11
    ç¾İæĦŁ
    0.11
    å®īåħ¨æĦŁ
    0.10
    ä¹°çļĦ
    0.10
    è´Ńä¹°
    0.10
    çIJ¨
    0.10
    izo
    0.10
    åĵģçīĮ
    0.10
    Activations Density 0.091%

    No Known Activations