© 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. 32890
    Prev
    Next
    INDEX
    Explanations

    belonging to

    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
    äºĨä»ĸçļĦ
    -0.11
    æİīäºĨ
    -0.10
    äºĨ许å¤ļ
    -0.10
    飩
    -0.10
    oon
    -0.10
    oom
    -0.10
    Ñģов
    -0.09
    缸åħ³åĨħ容
    -0.09
    æİī
    -0.09
    äºĨæĪijçļĦ
    -0.09
    POSITIVE LOGITS
    odal
    0.11
    è¿Ļ个ä¸ĸçķĮ
    0.10
    ä¸įå±ŀäºİ
    0.10
    Öģ
    0.09
    è¿Ļ个æĹ¶ä»£
    0.09
    ritt
    0.09
    ä¹Łæĺ¯ä¸Ģç§į
    0.08
    è¿Ļ个è¡Įä¸ļ
    0.08
    åĵªä¸ª
    0.08
    åı«
    0.08
    Activations Density 0.071%

    No Known Activations