© 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. 61558
    Prev
    Next
    INDEX
    Explanations

    related to harsh environments

    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
    躲éģ¿
    -0.10
    æĭįæĭį
    -0.09
    åī¡
    -0.09
    Ñģка
    -0.09
    æĭį
    -0.09
     Mae
    -0.08
    åIJ¬è¯Ŀ
    -0.08
    æĩĴ
    -0.08
     coverage
    -0.08
    èĪįä¸įå¾Ĺ
    -0.08
    POSITIVE LOGITS
     rugged
    0.11
    é©¿
    0.10
    æ³°å±±
    0.09
     DISCLAIMS
    0.09
    éĩİå¤ĸ
    0.09
    åĿļåĽº
    0.09
    ãĥĥãĤ·
    0.09
    æ¯ħ
    0.09
    ç«Ļéķ¿
    0.08
    ENC
    0.08
    Activations Density 0.098%

    No Known Activations