© 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. 54824
    Prev
    Next
    INDEX
    Explanations

    Cyprus and its abbreviations

    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
    ings
    -0.10
    층
    -0.09
    ²
    -0.09
    liness
    -0.09
    ays
    -0.08
    å¥ij
    -0.08
    æĸ¯åŁº
    -0.08
    ish
    -0.08
    æĬ¥éħ¬
    -0.08
    ÑĢаÑģ
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.12
    thon
    0.10
    adol
    0.10
    orical
    0.09
    teenth
    0.09
    reek
    0.09
    好è¿IJ
    0.09
     bầu
    0.09
    REE
    0.09
    ettel
    0.09
    Activations Density 0.024%

    No Known Activations