© 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. 8523
    Prev
    Next
    INDEX
    Explanations

    inner or inside

    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
    èĦ¸èī²
    -0.10
    ä¸Ģç¢Ĺ
    -0.09
    ivel
    -0.09
    è¯ļæĦı
    -0.09
    è§Ĩ线
    -0.09
    éĿ©
    -0.08
    porto
    -0.08
    lug
    -0.08
    .tech
    -0.08
    身价
    -0.08
    POSITIVE LOGITS
     tiá»ģm
    0.10
    èĹı
    0.10
    åľ¨éĩĮéĿ¢
    0.09
    æĿ¥å®¾
    0.09
    åģļ大
    0.09
     dormant
    0.09
     ХоÑĤ
    0.09
    æ¸´æľĽ
    0.09
    ä½ĵåĨħ
    0.09
    ä¸įåĩºæĿ¥
    0.09
    Activations Density 0.036%

    No Known Activations