© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9613
    Prev
    Next
    INDEX
    Explanations

    Quakers, Mennonites, Friends

    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
    建çŃijä¸ļ
    -0.11
    è¿ĻåĿĹ
    -0.10
    arendra
    -0.09
     facto
    -0.09
    è·Łè¿Ľ
    -0.09
    æ¿Ģåıij
    -0.09
    èº
    -0.08
     Eins
    -0.08
    oint
    -0.08
    jk
    -0.08
    POSITIVE LOGITS
    é¹Ń
    0.10
    èĶ¼
    0.09
     bend
    0.09
    IDGE
    0.09
    åľ¨è¿ĩ渡
    0.09
    çĶ¨è½¦
    0.08
    禾
    0.08
    æ¼ı
    0.08
    dom
    0.08
    æĮ½
    0.08
    Activations Density 0.004%

    No Known Activations