© 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. 36938
    Prev
    Next
    INDEX
    Explanations

    googled

    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
    æĬĬè¿Ļ个
    -0.09
    _STRUCTURE
    -0.09
    åĽŀè´Ń
    -0.09
    วà¸Ļ
    -0.08
    æĬĬè¿ĻäºĽ
    -0.08
    ses
    -0.08
    .timestamps
    -0.08
    SSION
    -0.08
    æĸ¹å½¢
    -0.08
    è²Į
    -0.08
    POSITIVE LOGITS
    ulously
    0.10
    erty
    0.10
    ç»ĵå±Ģ
    0.10
    éķ°
    0.09
    çıij
    0.09
    .jasper
    0.09
    onders
    0.09
     поиÑģк
    0.09
    çİĩè¾¾
    0.09
    å®ŀè´¨æĢ§
    0.09
    Activations Density 0.012%

    No Known Activations