© 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. 1781
    Prev
    Next
    INDEX
    Explanations

    this year’s

    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
    èĩªåªĴä½ĵ
    -0.11
    鬲
    -0.11
    ä¸ĢåĽ¢
    -0.10
    åij¨åĪĬ
    -0.10
    ä¸Ģåı£
    -0.09
    è¿ĩåİ»çļĦ
    -0.09
    ä¸Ģè¾ĪåŃIJ
    -0.09
    大海
    -0.09
    çĹ
    -0.09
    ä¸ĢåĪĩéĥ½
    -0.09
    POSITIVE LOGITS
    éĿ¢è²Į
    0.09
    ä½¼
    0.09
    çĶ·å¥³
    0.09
    ogh
    0.08
    éľĢè¦ģçĶ¨åĪ°
    0.08
    лÑĮн
    0.08
    é«ĺä½İ
    0.08
    åįģä¸ĥæĿ¡
    0.08
     compromise
    0.08
     rumours
    0.08
    Activations Density 0.013%

    No Known Activations