© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19453
    Prev
    Next
    INDEX
    Explanations

    code comments and copyright notices

    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
    WithIdentifier
    -0.08
     LW
    -0.08
    hiro
    -0.08
    NotBlank
    -0.08
    aic
    -0.08
    æĴĤ
    -0.08
    èĬ¥
    -0.08
    LineEdit
    -0.08
    åĪ«çļĦ
    -0.08
    _vec
    -0.08
    POSITIVE LOGITS
    .aspx
    0.19
    .xaml
    0.15
     Xamarin
    0.15
    IEnumerable
    0.15
    #endregion
    0.14
    .cs
    0.14
    ($"{
    0.14
    (@"
    0.14
     IEnumerable
    0.13
    ($"
    0.13
    Activations Density 2.370%

    No Known Activations