© 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. 50464
    Prev
    Next
    INDEX
    Explanations

    blog and website navigation

    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
    ANI
    -0.09
    orman
    -0.09
    ä»ŀ
    -0.09
    åĮį
    -0.09
    æijĺ
    -0.08
    èģĺ请
    -0.08
    çĤĻ
    -0.08
    ä¹Łä¸įæķ¢
    -0.08
    onus
    -0.08
    Ắ
    -0.08
    POSITIVE LOGITS
    xxx
    0.08
     Sle
    0.08
     xxx
    0.08
     STM
    0.08
    å¤ĸ
    0.08
    é«ĺçļĦ
    0.08
    éĻ·
    0.08
    å¾Īé«ĺ
    0.08
    ä¸įåıĺ
    0.08
     blog
    0.08
    Activations Density 0.029%

    No Known Activations