© 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. 50481
    Prev
    Next
    INDEX
    Explanations

    search and display information

    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
    æĹłåĬĽ
    -0.09
     Heard
    -0.09
    å°ıå¿ĥ
    -0.09
    èĽĬ
    -0.09
    å¤įæŁ¥
    -0.09
    éķ«
    -0.08
    ä¼ij
    -0.08
    碣
    -0.08
    å¦Ĥæŀľä½łæĥ³
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.08
    POSITIVE LOGITS
    ä¸ºçĽ®çļĦ
    0.09
    ä¸ĵå±ŀ
    0.09
    人群ä¸Ń
    0.09
    éĴĪ对æĢ§
    0.09
    çīµå¼ķ
    0.08
    odus
    0.08
    ÑĩаÑĤ
    0.08
     unbiased
    0.08
    noinspection
    0.08
    æ°ijå±ħ
    0.08
    Activations Density 0.036%

    No Known Activations