© 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. 3688
    Prev
    Next
    INDEX
    Explanations

    closing bracket or period followed by word

    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
    /OR
    -0.10
    esson
    -0.08
    æĪij们çļĦ
    -0.08
    è¿Ļæĺ¯æĪij们
    -0.07
    çŃĶåºĶ
    -0.07
    ãģ»ãģ¨
    -0.07
    æ¿Ģ
    -0.07
    ä¸įè¡Į
    -0.07
    æł·çļĦ
    -0.07
    赶快
    -0.07
    POSITIVE LOGITS
    abra
    0.10
    åĵ¦
    0.10
    ç²
    0.10
    ogra
    0.09
    温馨æıIJ示
    0.09
    åĩºåĩ»
    0.09
    alto
    0.09
    remely
    0.09
    管çIJĨåĴĮ
    0.08
    åĶ®
    0.08
    Activations Density 0.594%

    No Known Activations