© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21116
    Prev
    Next
    INDEX
    Explanations

    cope, compete, comply, respond

    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
    /from
    -0.15
    éģįåıĬ
    -0.09
    æĪĸå¤ļ
    -0.09
    ÑĢÑĥж
    -0.09
    /on
    -0.09
    going
    -0.09
    /out
    -0.08
    hib
    -0.08
    æĪijèĩªå·±
    -0.08
    è¿Ħ
    -0.08
    POSITIVE LOGITS
    enticate
    0.11
     thêm
    0.11
    ivate
    0.10
    ingly
    0.10
    annis
    0.10
    uate
    0.10
    èĮ¹
    0.10
    ently
    0.10
    ä½Ŀ
    0.09
    äºİ
    0.09
    Activations Density 0.354%

    No Known Activations