© 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. 57084
    Prev
    Next
    INDEX
    Explanations

    life's purpose and mission

    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
    æ²±
    -0.09
    èĪĬ
    -0.09
    æŧ
    -0.09
     Cra
    -0.09
    éĩįè§Ĩ
    -0.09
    媵
    -0.08
    _keywords
    -0.08
    çľĭéĩį
    -0.08
    é¢ģåıij
    -0.08
    èļķ
    -0.08
    POSITIVE LOGITS
    èĩ´åĬĽäºİ
    0.11
    éŀį
    0.10
    èĩ´åĬĽ
    0.09
    çłĶ究
    0.09
     mission
    0.09
    æĶ»åħĭ
    0.09
    æݢ索
    0.09
    åѦéĹ®
    0.09
    ä¸ĵèģĮ
    0.09
    æĭ¯æķij
    0.08
    Activations Density 0.035%

    No Known Activations