© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37282
    Prev
    Next
    INDEX
    Explanations

    bluetooth and connectivity

    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
    æĬ¥éħ¬
    -0.09
    åģı
    -0.09
     loot
    -0.08
    quisites
    -0.08
    tle
    -0.08
    lords
    -0.08
    ä¸įéĶĪéĴ¢
    -0.08
    ites
    -0.08
     dif
    -0.08
    omes
    -0.08
    POSITIVE LOGITS
    agh
    0.10
    åħļç»Ħ
    0.10
    è¿ĻçĤ¹
    0.09
    ìĩ¼
    0.09
    èĢķ
    0.09
    åŀĴ
    0.09
    PEAR
    0.09
    rne
    0.09
    aseline
    0.09
     воÑĤ
    0.09
    Activations Density 0.003%

    No Known Activations