© 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. 34012
    Prev
    Next
    INDEX
    Explanations

    haven't + verb

    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
    æĽ¾ç»ı
    -0.10
    intptr
    -0.09
    HasBeen
    -0.09
    _OCC
    -0.09
    BUFF
    -0.09
    æĽ¾
    -0.09
    ä»Ģä¹ĪæĦıæĢĿ
    -0.09
     Dzi
    -0.09
    便
    -0.09
    RuntimeObject
    -0.09
    POSITIVE LOGITS
    essian
    0.10
    aise
    0.09
     sido
    0.09
    å°ļæľª
    0.09
    è§
    0.09
    виÑĤ
    0.09
    arians
    0.08
    metics
    0.08
    forth
    0.08
    zn
    0.08
    Activations Density 0.027%

    No Known Activations