© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52692
    Prev
    Next
    INDEX
    Explanations

    one or more

    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
    QUIRE
    -0.10
    emes
    -0.10
    queryString
    -0.09
     thụ
    -0.09
    serrat
    -0.09
    ãĥ¡ãĥ¼ãĤ
    -0.09
    ONGL
    -0.08
    ymes
    -0.08
    lama
    -0.08
    æł©
    -0.08
    POSITIVE LOGITS
    è¾ĩ
    0.10
    ä¸Ģ个éĩįè¦ģ
    0.09
    ä¸įä¹ı
    0.09
    ç»ıå¼Ģ
    0.08
    ç´§åĩij
    0.08
    ä¸įæİĴéĻ¤
    0.08
    é¢Ŀ头
    0.08
    å°ķ
    0.08
    è´¢è¿IJ
    0.08
    åħīéĺ´
    0.08
    Activations Density 0.122%

    No Known Activations