© 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. 1990
    Prev
    Next
    INDEX
    Explanations

    million (money)

    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
    æĿĢ
    -0.08
    ÑĪен
    -0.08
    øj
    -0.08
    2
    -0.08
    dT
    -0.08
    5
    -0.08
    åĮºåĪ«
    -0.08
    åľ¨æĪijåĽ½
    -0.08
    éĢĿ
    -0.07
    åĶ¯ä¸Ģ
    -0.07
    POSITIVE LOGITS
    ium
    0.11
    éĮ
    0.10
    åĦĨ
    0.09
    æ²Ļé¾Ļ
    0.09
    ä¸Ģåı£æ°Ķ
    0.09
    以èī²
    0.09
    abyrinth
    0.09
    andes
    0.08
     rosa
    0.08
    arie
    0.08
    Activations Density 0.094%

    No Known Activations