© 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. 32790
    Prev
    Next
    INDEX
    Explanations

    D followed by numbers or abbreviations

    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
    缮åħī
    -0.08
     bile
    -0.08
    herits
    -0.08
    олоÑģ
    -0.08
    IFA
    -0.08
    åħ³
    -0.08
    æľĢ好çļĦ
    -0.08
     stead
    -0.08
     once
    -0.08
    ullo
    -0.08
    POSITIVE LOGITS
    ply
    0.11
    iane
    0.09
    æĢ§åĴĮ
    0.09
    çIJ¨
    0.09
    ploy
    0.09
     вÑģей
    0.09
    è´¶
    0.08
     недо
    0.08
    ãģĭãģij
    0.08
    vanced
    0.08
    Activations Density 0.116%

    No Known Activations