© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8135
    Prev
    Next
    INDEX
    Explanations

    other / others

    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
    esti
    -0.10
    benh
    -0.10
    åĨį度
    -0.10
    cki
    -0.10
     ÑħозÑıй
    -0.09
     Angelo
    -0.09
    hea
    -0.09
    æĸ°éĹ»åıijå¸ĥ
    -0.08
    è¹²
    -0.08
    蹶
    -0.08
    POSITIVE LOGITS
    纷纷
    0.12
    ä¸Ģ个个
    0.11
    åħ¶ä»ĸçݩ家
    0.10
    è·Łä»ĸ
    0.10
    åħ¶ä»ĸ
    0.10
    è·Łå¥¹
    0.09
    ä¸įåIJĮç¨ĭ度
    0.09
     other
    0.09
    讨
    0.09
    缸æ¯Ķä¹ĭä¸ĭ
    0.09
    Activations Density 0.105%

    No Known Activations