© 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. 37677
    Prev
    Next
    INDEX
    Explanations

    Henley, weekend, Henman, Henan

    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
     ведÑĮ
    -0.09
    æĻŀ
    -0.09
    ãģľ
    -0.09
    -Isl
    -0.09
    èݹ
    -0.09
    äºĽä»Ģä¹Ī
    -0.09
    人寿
    -0.08
    èĢģçĪ·åŃIJ
    -0.08
    éĻIJéĩı
    -0.08
    åĪĿæģĭ
    -0.08
    POSITIVE LOGITS
    ings
    0.10
    éļĹ
    0.10
    iqu
    0.09
    ç³Ĭ
    0.09
    bling
    0.09
    mates
    0.09
    lessness
    0.09
     dolayı
    0.09
    rique
    0.09
    velt
    0.08
    Activations Density 0.006%

    No Known Activations