© 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. 21487
    Prev
    Next
    INDEX
    Explanations

    php template includes

    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
    æĢ»éĺŁ
    -0.10
    伺
    -0.09
    èįī
    -0.09
    容
    -0.09
     PAC
    -0.08
    æĸĩæĺİ
    -0.08
    è±
    -0.08
    æĭĽ
    -0.08
    äºĴèģĶ
    -0.08
    æ¸ħæ°´
    -0.08
    POSITIVE LOGITS
    产åĮº
    0.09
    igit
    0.09
    鼶åĶ®åķĨ
    0.09
    åĵĦ
    0.09
    .cuda
    0.09
    atest
    0.09
    ä¸Ģå¤ľ
    0.09
    alers
    0.09
    è´¸æĺĵ
    0.08
    ä¸įä¸Ĭ
    0.08
    Activations Density 0.215%

    No Known Activations