© 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. 51924
    Prev
    Next
    INDEX
    Explanations

    Chinese/Japanese/Korean script

    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
    rott
    -0.09
    راب
    -0.09
     Licence
    -0.09
    getPost
    -0.08
     sacrific
    -0.08
    åħ¥å¸Ĥ
    -0.08
    osto
    -0.08
    æ¶Ī
    -0.08
    çīºçī²
    -0.08
    ç¾İåĮĸ
    -0.08
    POSITIVE LOGITS
    è¯ķåį·
    0.15
    ä¸Ģéģĵ
    0.14
    è¯ķé¢ĺ
    0.14
    é¢ĺ
    0.13
    é¢ĺ缮
    0.13
    é¡Į
    0.13
    çŃĶé¢ĺ
    0.13
    éĺħ
    0.10
    åij½é¢ĺ
    0.10
    çijĻ
    0.10
    Activations Density 0.103%

    No Known Activations