© 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. 23308
    Prev
    Next
    INDEX
    Explanations

    required by law

    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
    æµĨ
    -0.10
    ç»Ń
    -0.09
     ÐijеÑģ
    -0.09
    è¿ŀè½½
    -0.08
    ä¸įæĪIJ
    -0.08
    å»ĵ
    -0.08
    åľ¨å¹¿å·ŀ
    -0.08
    bat
    -0.08
    éķIJ
    -0.08
    çĶľ
    -0.08
    POSITIVE LOGITS
    ä¾Ŀçħ§
    0.10
    å²Ľä¸Ĭ
    0.09
    åĬ¡å®ŀ
    0.09
    å¼ĢåĬŀ
    0.09
    åıijæĮ¥ä½ľçĶ¨
    0.09
    æĩ¦
    0.09
    å²Ľ
    0.09
    ìĤ¬íķŃ
    0.09
    夥
    0.09
    æ³ķå¾ĭæ³ķè§Ħ
    0.08
    Activations Density 0.048%

    No Known Activations