© 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. 30818
    Prev
    Next
    INDEX
    Explanations

    later

    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
    缮åīį
    -0.15
    缮åīįå·²
    -0.14
    æѤæŶ
    -0.14
    缮åīįæŃ£åľ¨
    -0.14
     currently
    -0.13
    çİ°åľ¨å·²ç»ı
    -0.13
    æľĢåIJİ
    -0.12
    缮åīįå·²ç»ı
    -0.12
     ÑģейÑĩаÑģ
    -0.12
    é¦ĸåħĪè¦ģ
    -0.12
    POSITIVE LOGITS
    è¿ĺä¼ļ
    0.11
     Later
    0.10
    (after
    0.10
     later
    0.09
    later
    0.09
    Later
    0.09
    åĽŀæĿ¥
    0.09
     später
    0.09
    igator
    0.08
    è¿ĺå°Ĩ
    0.08
    Activations Density 0.083%

    No Known Activations