© 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. 30135
    Prev
    Next
    INDEX
    Explanations

    due 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
    è®®æ¡Ī
    -0.09
    æīĪ
    -0.09
    ä½ıäºĨ
    -0.09
    åļ¼
    -0.09
    çĤ¹äºĨ
    -0.09
    è¿Ļ个èģĮä¸ļ
    -0.08
    _bd
    -0.08
    åı¯çĸij
    -0.08
    ä¹ĭæĪĺ
    -0.08
    åĵ¨
    -0.08
    POSITIVE LOGITS
    涤
    0.09
    .experimental
    0.09
    ANTS
    0.09
    åIJĪæ³ķæĢ§
    0.09
    UFF
    0.09
    ató
    0.09
    åıijæĮ¥ä½ľçĶ¨
    0.09
    عب
    0.08
    woocommerce
    0.08
    åĪ°ä½į
    0.08
    Activations Density 0.015%

    No Known Activations