© 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. 37702
    Prev
    Next
    INDEX
    Explanations

    attract attention

    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
    æĪŁ
    -0.09
    çħ³
    -0.09
    ÑĤов
    -0.09
    formed
    -0.09
    owanie
    -0.08
    èĮµ
    -0.08
    pping
    -0.08
    cial
    -0.08
    触åĬ¨
    -0.08
    nton
    -0.08
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.12
    æѤäºĭ
    0.10
    OrElse
    0.10
    ìĤ¬íķŃ
    0.09
    al
    0.09
    иж
    0.09
     лиÑĪÑĮ
    0.09
    alah
    0.09
    æĢ
    0.09
    ãģıãģłãģķãģĦ
    0.08
    Activations Density 0.019%

    No Known Activations