© 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. 53324
    Prev
    Next
    INDEX
    Explanations

    describing past states or situations

    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
    éĽĨ
    -0.09
    èĢĨ
    -0.09
    åľ°ä¸Ńæµ·
    -0.09
    é¦ı
    -0.09
    å¡«
    -0.09
    ä¸IJ
    -0.08
     bre
    -0.08
    .after
    -0.08
    车ä½į
    -0.08
    è·Ħ
    -0.08
    POSITIVE LOGITS
    åıijçĥ§
    0.10
    æĿŁ
    0.09
    å¿Ĺ强
    0.09
    zsche
    0.09
    æĺ¯ä¸ª
    0.09
    伤
    0.09
     Fro
    0.09
    ä½ľæĸĩ
    0.08
    åĨį说
    0.08
    çĴł
    0.08
    Activations Density 0.054%

    No Known Activations