© 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. 4118
    Prev
    Next
    INDEX
    Explanations

    MacDonald or McDonald names

    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
    lessly
    -0.09
     Jeg
    -0.08
    åĥı个
    -0.08
    ules
    -0.08
    æ¥Ķ
    -0.08
    åIJ¸æĶ¶
    -0.08
    鸳
    -0.08
    åĵī
    -0.08
    outh
    -0.08
    umm
    -0.08
    POSITIVE LOGITS
    roe
    0.10
    ÑĤÑĭ
    0.09
    requestData
    0.08
    yme
    0.08
    дÑĢеÑģ
    0.08
    .tc
    0.08
    å°ıç¼ĸ
    0.08
    IFT
    0.08
    æŃ¤ä¸¾
    0.08
    arez
    0.08
    Activations Density 0.005%

    No Known Activations