© 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. 30687
    Prev
    Next
    INDEX
    Explanations

    website content types

    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
    ä¹ĭ声
    -0.09
    éĢļä¿¡
    -0.09
    è¶ħé¢Ŀ
    -0.09
    åŁİå¸Ĥ群
    -0.08
    çİ«çij°
    -0.08
    åķĸ
    -0.08
    æĩ¿
    -0.08
    .credentials
    -0.08
    é©Ń
    -0.08
    æ½ľæ°´
    -0.08
    POSITIVE LOGITS
    åħįè´¹
    0.11
    åħįè²»
    0.09
    大åħ¨
    0.09
     Hanna
    0.09
    agal
    0.09
    ä¹ħä¹ħ
    0.08
    çĶ·å¥³
    0.08
     Free
    0.08
    æºIJ头
    0.08
    Free
    0.08
    Activations Density 0.126%

    No Known Activations