© 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. 17337
    Prev
    Next
    INDEX
    Explanations

    text that sets up a noun or event

    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
    ImageContext
    -0.09
    ä¸ĢæŶ
    -0.09
     getSession
    -0.08
    以åīį
    -0.08
    ä¸Ģå®ļçļĦ
    -0.08
    æľīå¾Ī大
    -0.08
    åѦåİĨ
    -0.08
    .training
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.08
    åĩĨ
    -0.08
    POSITIVE LOGITS
    åĭº
    0.10
    å¿ħä¸įåı¯
    0.09
    awan
    0.09
    undy
    0.09
    ims
    0.09
    æľīåIJį
    0.09
    éļ¾å¿ĺ
    0.09
    åķ¼
    0.08
    urre
    0.08
     aforementioned
    0.08
    Activations Density 0.051%

    No Known Activations