© 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. 36635
    Prev
    Next
    INDEX
    Explanations

    points of interest, initiation, sale, view

    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
    åºŁè¯Ŀ
    -0.10
    岿
    -0.09
    éŃĶ鬼
    -0.09
    UNT
    -0.09
    æĶ¾ç½®
    -0.09
    .cn
    -0.09
    оÑĦ
    -0.08
    鼳
    -0.08
    æ²Ļåıijä¸Ĭ
    -0.08
    Hell
    -0.08
    POSITIVE LOGITS
    æī£
    0.10
    dro
    0.09
    EDIA
    0.09
    çĦ¶
    0.09
    point
    0.09
    宿
    0.08
    æĮĤåľ¨
    0.08
    ADER
    0.08
    amble
    0.08
    mony
    0.08
    Activations Density 0.025%

    No Known Activations