© 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. 34852
    Prev
    Next
    INDEX
    Explanations

    time for

    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
    åºĶ该å¦Ĥä½ķ
    -0.11
    ifter
    -0.10
    é¹Ħ
    -0.10
    ä¼Ĭæĸ¯
    -0.09
    åįĸåľº
    -0.09
    çİ°è¡Į
    -0.09
    读æĩĤ
    -0.09
    éªİ
    -0.09
    è¶Ĭè¿ĩ
    -0.09
    æĺ¯å¦Ĥä½ķ
    -0.09
    POSITIVE LOGITS
    æ²ī
    0.09
     suf
    0.08
    ocs
    0.08
    å©Ĩ
    0.08
     Ctrl
    0.08
    强çĥĪçļĦ
    0.08
    对è¯Ŀ
    0.08
    æ·¡
    0.08
    tk
    0.08
     MK
    0.08
    Activations Density 0.061%

    No Known Activations