© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20978
    Prev
    Next
    INDEX
    Explanations

    every time

    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
    æĹ¢æľī
    -0.10
    åĪ«
    -0.10
    çªģ
    -0.09
    é¢ŀ
    -0.09
    æĺİå¹´
    -0.09
    缨
    -0.09
    忽
    -0.08
    åħ¨éĿ¢
    -0.08
     Elite
    -0.08
    illa
    -0.08
    POSITIVE LOGITS
    åĩºå·®
    0.10
    à¹Ģสมà¸Ń
    0.10
    ä¸Ģè´¯
    0.10
    åı¯éĿłçļĦ
    0.10
    çĻ¾åĪĨä¹ĭ
    0.09
     Reliable
    0.09
    ä¸į论
    0.09
    åı¯éĿł
    0.09
    OfSize
    0.09
    票
    0.09
    Activations Density 0.057%

    No Known Activations