© 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. 2974
    Prev
    Next
    INDEX
    Explanations

    world, universe, end, all

    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
    é«ĺ级
    -0.10
    IBC
    -0.09
    æĦĪ
    -0.09
    æĴ¤ç¦»
    -0.09
    æ´Ĺè¡£
    -0.08
    为主
    -0.08
    adow
    -0.08
    sing
    -0.08
     láºŃp
    -0.08
    ç«ĭ
    -0.08
    POSITIVE LOGITS
     universe
    0.15
    å®ĩå®Ļ
    0.15
    ä¸ĸçķĮçļĦ
    0.14
    ä¸ĸçķĮä¸Ĭ
    0.14
    åľ°çIJĥ
    0.14
    ä¸ĸçķĮä¸ĬæľĢ
    0.13
     Universe
    0.13
    ä¸ĸçķĮ
    0.13
    åħ¨ä¸ĸçķĮ
    0.13
    å¤©åľ°
    0.12
    Activations Density 0.058%

    No Known Activations