© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22909
    Prev
    Next
    INDEX
    Explanations

    conveyor belt elevator carousel escalator

    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
    åºŁ
    -0.11
    大å¸Ī
    -0.09
    æ¸ħåįİ
    -0.09
    娥
    -0.09
    scoped
    -0.09
    æĭ§
    -0.09
    æĮģ
    -0.08
     busted
    -0.08
    iesel
    -0.08
    1
    -0.08
    POSITIVE LOGITS
    沫
    0.11
    åĽ¢
    0.09
    ego
    0.09
    ä»·æł¼ä¸Ĭ涨
    0.09
    ä¸ĵéŨ
    0.09
    ä¸Ĭãģ§
    0.09
    åĬŁåĬĽ
    0.08
    è¿Ľç¨ĭä¸Ń
    0.08
     ÄijoÃłn
    0.08
    è¿Ļç§įæĸ¹å¼ı
    0.08
    Activations Density 0.040%

    No Known Activations