© 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. 38439
    Prev
    Next
    INDEX
    Explanations

    previous navigation or xhtml

    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
    宣åijĬ
    -0.09
    饼
    -0.08
     Barg
    -0.08
    å°¼äºļ
    -0.08
    неÑĨ
    -0.08
    KEN
    -0.08
    .Parcel
    -0.08
    .datab
    -0.08
    .Dispatcher
    -0.08
    移åĬ¨ç«¯
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸įä¼ļ
    0.09
    edException
    0.09
    èħĪ
    0.09
    æŀķ
    0.09
    æ·¡æ·¡çļĦ
    0.08
    apur
    0.08
    æļĩ
    0.08
    inci
    0.08
    ariat
    0.08
    èij«
    0.08
    Activations Density 0.008%

    No Known Activations