© 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. 55810
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation delimiters

    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
    zes
    -0.10
    ç¡IJ
    -0.08
    åħ¶å®ĥ
    -0.08
    ainers
    -0.08
    åīĬ
    -0.08
    urr
    -0.08
    MSN
    -0.08
    á»ħ
    -0.08
    è¿ĩ硬
    -0.08
    çķ¶æĤ¨åľ¨
    -0.08
    POSITIVE LOGITS
    åĩłåı¥
    0.11
    è¿Ļ段
    0.10
     Engl
    0.09
    ä»Ģä¹ĪæĦıæĢĿ
    0.09
    _eng
    0.09
    çĤ¹åĦ¿
    0.09
     frank
    0.09
    稼
    0.09
    éĻĪè¿°
    0.09
    æĢİä¹Ī说
    0.09
    Activations Density 0.009%

    No Known Activations