© 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. 22014
    Prev
    Next
    INDEX
    Explanations

    salvation from, Unless required

    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
    积èĵĦ
    -0.09
    让å®ĥ
    -0.09
    èĥŃ
    -0.09
    inke
    -0.09
    pler
    -0.09
    é¦Ĩ
    -0.09
    客æĪ¿
    -0.09
    ãĥ¼ãĤº
    -0.09
    丰å¯Į
    -0.09
    åıįåĵį
    -0.09
    POSITIVE LOGITS
     Zub
    0.09
    ä¹ĭéģĵ
    0.09
    Reusable
    0.09
    Formats
    0.08
    ë§IJ
    0.08
    æĶ¥
    0.08
    çªľ
    0.08
     Serie
    0.08
    å®ĮæĪIJäºĨ
    0.08
    lest
    0.08
    Activations Density 0.026%

    No Known Activations