© 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. 22314
    Prev
    Next
    INDEX
    Explanations

    alphabetical sorting

    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
    æĩĪ
    -0.10
    ç¼ļ
    -0.10
    çĶļèĩ³è¿ŀ
    -0.09
     Pale
    -0.09
    angen
    -0.08
    åĮĹ大
    -0.08
    à¸Ńา
    -0.08
    éĩĬ
    -0.08
    ITA
    -0.08
    arendra
    -0.08
    POSITIVE LOGITS
    plorer
    0.09
    è°£
    0.09
    èĵĿ天
    0.09
    èĽĬ
    0.09
    çķĮçļĦ
    0.09
    ool
    0.08
    çĸĶ
    0.08
    arians
    0.08
    åıĻ
    0.08
    etro
    0.08
    Activations Density 0.016%

    No Known Activations