© 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. 37279
    Prev
    Next
    INDEX
    Explanations

    onlyallow, has, want, stores, gets, trigger, have

    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
    otate
    -0.09
    AVA
    -0.09
    /slick
    -0.09
    è¿
    -0.09
    èĢĮä¸įæĺ¯
    -0.09
    ãģĭãģĦ
    -0.09
    è¿ĺè¦ģ
    -0.09
    è¿Ļå°±æĺ¯
    -0.08
    ä¹Łä¸įçŁ¥éģĵ
    -0.08
    没人
    -0.08
    POSITIVE LOGITS
     лиÑĪÑĮ
    0.12
    ä¸Ģ次
    0.11
    ä¸Ģ件äºĭ
    0.09
    ä¸Ģéģį
    0.09
    åĭī强
    0.08
    urs
    0.08
     Binder
    0.08
     Joy
    0.08
    Explorer
    0.08
    åĶ¯ä¸ĢçļĦ
    0.08
    Activations Density 0.047%

    No Known Activations