© 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. 8158
    Prev
    Next
    INDEX
    Explanations

    includes especially gather his do and write

    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
    urr
    -0.09
    Ùĭا
    -0.09
    ìĿ´ê³ł
    -0.08
    nbsp
    -0.08
    çİ
    -0.08
    [](
    -0.08
    微信åı·
    -0.08
    ãģĤãĤĬãģ¾ãģĻãģĮ
    -0.08
    æĿIJ
    -0.08
    world
    -0.08
    POSITIVE LOGITS
    ÑģÑı
    0.10
    entication
    0.10
    naire
    0.09
    è¡·
    0.09
    ably
    0.08
    angu
    0.08
    ongs
    0.08
    çŀĦåĩĨ
    0.08
    ienza
    0.08
    åľ°ä¸Ń
    0.08
    Activations Density 0.064%

    No Known Activations