© 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. 27814
    Prev
    Next
    INDEX
    Explanations

    according to data

    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
    èİ«
    -0.10
    æ´Ĺ涤
    -0.09
    iali
    -0.09
    åľ¨æł¡
    -0.09
    è¾Ħ
    -0.09
    hood
    -0.09
    äºŃ
    -0.09
    åģ·
    -0.08
    æĶ¾åѦ
    -0.08
     новоÑģÑĤи
    -0.08
    POSITIVE LOGITS
    ä¸įä¹ħåīį
    0.10
    æľĢè¿ij
    0.10
    åħ³åı£
    0.10
    åıĺåĬ¨
    0.10
    宸
    0.09
    æľĢæĸ°çļĦ
    0.09
    æľĢæĸ°
    0.09
     recent
    0.08
    лом
    0.08
     Tall
    0.08
    Activations Density 0.095%

    No Known Activations