© 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. 19328
    Prev
    Next
    INDEX
    Explanations

    following, preceding, succeeded, comes next

    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
    çĹĽ
    -0.09
    chie
    -0.09
    æľį
    -0.09
    aten
    -0.09
    ä¹į
    -0.09
    纳åħ¥
    -0.09
    åºķå±Ĥ
    -0.08
    庶
    -0.08
    æĿĪ
    -0.08
    rosse
    -0.08
    POSITIVE LOGITS
    继
    0.14
    æİ¥çĿĢ
    0.12
     preceding
    0.12
    ç¹¼
    0.12
    æĹłç¼Ŀ
    0.11
    è¡Ķæİ¥
    0.11
    preced
    0.11
    æİ¥
    0.11
     preceded
    0.11
    è·Łè¿Ľ
    0.11
    Activations Density 0.093%

    No Known Activations