© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38981
    Prev
    Next
    INDEX
    Explanations

    Valentine's Day

    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
    cpt
    -0.09
     Nad
    -0.09
    DW
    -0.09
    sey
    -0.09
    åľĥ
    -0.09
     trg
    -0.08
    å®Ľ
    -0.08
     DW
    -0.08
    ä¸Ńå¤ĸ
    -0.08
    天ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    è¾Ļ
    0.09
     Scha
    0.09
    Elite
    0.08
    è¿Ļä½į
    0.08
    IA
    0.08
     اÙĦÙĥبÙĬر
    0.08
    æĴ¼
    0.08
    æĶ»åĬ¿
    0.08
    yo
    0.08
    为导åIJij
    0.08
    Activations Density 0.003%

    No Known Activations