© 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. 53060
    Prev
    Next
    INDEX
    Explanations

    terms of license

    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
    ebra
    -0.10
    åºĶæľīçļĦ
    -0.10
    å±ķæľĽ
    -0.10
    éĢĹ
    -0.09
    姿æĢģ
    -0.09
    Ëĥ
    -0.09
    sus
    -0.09
    姿
    -0.09
    rado
    -0.08
    ä¸į说
    -0.08
    POSITIVE LOGITS
    buzz
    0.11
    è¿Ļæĺ¯æĪij
    0.09
    bo
    0.09
    ä¸ķ
    0.08
    elder
    0.08
     Flesh
    0.08
    .googlecode
    0.08
     Seasons
    0.08
    æĺ¼å¤ľ
    0.08
    工夫
    0.08
    Activations Density 0.258%

    No Known Activations