© 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. 2764
    Prev
    Next
    INDEX
    Explanations

    the followed by noun

    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
    å¦Ĥæľīä¾µæĿĥ
    -0.10
    墨
    -0.10
    umpy
    -0.10
    ä»Ģä¹Īåij¢
    -0.09
    èļĢ
    -0.09
    alla
    -0.09
    æŶéĹ´åĴĮ
    -0.09
    èĻĵ
    -0.09
    ä½Ļ家
    -0.09
    å¢ĥåĨħ
    -0.09
    POSITIVE LOGITS
    ì°¬
    0.09
    ol
    0.08
    æĦŁãģĺ
    0.08
    åłµ
    0.08
     holidays
    0.08
     Sachs
    0.07
    à¹Ĥà¸Ľà¸£à¸Ķ
    0.07
     ur
    0.07
    红楼
    0.07
    èijĨ
    0.07
    Activations Density 0.134%

    No Known Activations