© 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. 26767
    Prev
    Next
    INDEX
    Explanations

    ssh connection and authentication

    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
    çĶŁäº§æĢ»åĢ¼
    -0.11
    å°ļ书
    -0.10
    æŀģåĬĽ
    -0.09
    getter
    -0.09
    å·©åĽº
    -0.09
    åľ¨æİ¥åıĹ
    -0.09
    ży
    -0.09
    ä¸ĢèĤ¡
    -0.09
    andro
    -0.09
    ÙĪرÙĪ
    -0.09
    POSITIVE LOGITS
    ilation
    0.09
    ikal
    0.09
    åĪº
    0.09
     налиÑĩ
    0.08
    é¦ĭ
    0.08
    ODE
    0.08
    碴
    0.08
    lation
    0.08
    >xpath
    0.08
    .Framework
    0.08
    Activations Density 0.033%

    No Known Activations