© 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. 17508
    Prev
    Next
    INDEX
    Explanations

    achieve higher, greater, good

    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
    åĭ¤å¥ĭ
    -0.10
    .mozilla
    -0.10
    æ½®
    -0.09
    ä¸įæĸŃå¢ŀ强
    -0.09
    ndo
    -0.09
    æİīäºĨ
    -0.09
    æĶ¹æĪIJ
    -0.09
    çķĽ
    -0.08
    tal
    -0.08
    (UI
    -0.08
    POSITIVE LOGITS
    çłĤ
    0.12
     goals
    0.10
    åıijå±ķ缮æłĩ
    0.09
    缮æłĩ
    0.09
     levels
    0.09
     mục
    0.09
    å±ķä½į
    0.09
    å±ĢéĿ¢
    0.09
    goals
    0.09
     ÑĥÑĢовнÑı
    0.09
    Activations Density 0.224%

    No Known Activations