© 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. 33365
    Prev
    Next
    INDEX
    Explanations

    determine something

    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
    沫
    -0.10
    ipur
    -0.09
    ä¸įç®¡ä½ł
    -0.09
    èĪĮ头
    -0.09
     regard
    -0.08
    åŃ¦ä¹łæĪIJ绩
    -0.08
    æ·±çŁ¥
    -0.08
    MLS
    -0.08
    .getElement
    -0.08
    å·¥ä½ľç»ıéªĮ
    -0.08
    POSITIVE LOGITS
    åľ¨åĵªéĩĮ
    0.12
    究竣æĺ¯
    0.12
    æĽ´å¤ļ精彩
    0.10
    åľ¨åĵª
    0.10
    åħ¶å®ŀå°±æĺ¯
    0.10
    ä½ķæŶ
    0.10
    åĩºå¤Ħ
    0.09
    èĽŃ
    0.09
    æĺ¯åIJ¦åŃĺåľ¨
    0.09
     worth
    0.09
    Activations Density 0.611%

    No Known Activations