© 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. 10018
    Prev
    Next
    INDEX
    Explanations

    others disagree

    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
    æ¿ij
    -0.08
     اÙĦÙĥÙĦ
    -0.08
    سئ
    -0.08
     SCAN
    -0.08
    纸ä¸Ĭ
    -0.08
    tring
    -0.08
    avia
    -0.08
     Wire
    -0.08
    è«ĸ
    -0.08
    çļĦç«ŀäºī
    -0.07
    POSITIVE LOGITS
    æĪij们认为
    0.13
    åį´æĺ¯
    0.13
    others
    0.12
    è§Ĵ度çľĭ
    0.12
    åħ¶ä»ĸ人
    0.11
    åį´
    0.11
     others
    0.11
     Others
    0.11
    Others
    0.11
    ä½ľèĢħæľ¬äºº
    0.11
    Activations Density 0.087%

    No Known Activations