© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7070
    Prev
    Next
    INDEX
    Explanations

    la-, lar-, port-, mar-, guard-, grande

    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
    离
    -0.10
    urses
    -0.10
    manuel
    -0.09
    ä¸įåłª
    -0.09
    ceptor
    -0.09
    utors
    -0.09
    stones
    -0.09
     наб
    -0.09
    WITHOUT
    -0.09
    åľ¨èģĮ
    -0.09
    POSITIVE LOGITS
    人æµģ
    0.09
    æ³ĵ
    0.09
    秽
    0.09
    ite
    0.08
    å¤īãĤıãģ£ãģ¦
    0.08
    åģļä¸įåĪ°
    0.08
    ä¸Ģç¯ĩ
    0.08
     latter
    0.08
    æij¸ç´¢
    0.08
    çĬ¶æĢģä¸ĭ
    0.08
    Activations Density 0.019%

    No Known Activations