© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5189
    Prev
    Next
    INDEX
    Explanations

    choose to read

    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
    .lesson
    -0.10
    ANEL
    -0.10
     Brewer
    -0.09
    .SDK
    -0.09
    IMER
    -0.09
    æķ´ä¸ªäºº
    -0.08
    åı¯æĥľ
    -0.08
    åŃĢ
    -0.08
     chimney
    -0.08
     Rosenstein
    -0.08
    POSITIVE LOGITS
    溢
    0.08
    è¨ĢãģĪãģ°
    0.08
    AndGet
    0.08
    cond
    0.08
     Rico
    0.08
    keh
    0.08
    å°±æĺ¯è¿Ļæł·
    0.08
    çĵ£
    0.07
     Ebook
    0.07
     Buzz
    0.07
    Activations Density 0.075%

    No Known Activations