© 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. 8136
    Prev
    Next
    INDEX
    Explanations

    later

    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
    èµŀ
    -0.09
    ä¸Ģ个å¤ļ
    -0.09
    bris
    -0.09
    鸳
    -0.08
    çŀ§
    -0.08
    姥
    -0.08
    ç®Ĺ
    -0.08
    rias
    -0.08
    ä¸Ĭç½ij
    -0.08
    çĶ¨å¿ĥ
    -0.08
    POSITIVE LOGITS
     later
    0.21
    Later
    0.18
     Later
    0.18
    later
    0.18
     später
    0.17
    åIJİæĿ¥
    0.15
    以åIJİ
    0.15
    åIJİç»Ń
    0.14
    æĹ¥åIJİ
    0.14
    åIJİæľŁ
    0.14
    Activations Density 0.065%

    No Known Activations