© 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. 8116
    Prev
    Next
    INDEX
    Explanations

    Page followed by Type or Area

    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
    ä¿Ł
    -0.09
    çİĸ
    -0.08
    ç¥Ń
    -0.08
    oser
    -0.08
     FAG
    -0.08
    å¤©åºľ
    -0.08
    Cong
    -0.08
    èĤºçĤİ
    -0.08
    迳
    -0.08
    ä¸įè´Ł
    -0.08
    POSITIVE LOGITS
    ype
    0.13
    YPE
    0.10
    ä¸Ģçķª
    0.10
    gaard
    0.10
    ç»Ī
    0.10
    æīĭèħķ
    0.09
    erview
    0.09
    å·½
    0.09
    æĤ²è§Ĥ
    0.09
    edor
    0.09
    Activations Density 0.031%

    No Known Activations