© 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. 39622
    Prev
    Next
    INDEX
    Explanations

    time-related prepositions

    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
    ouro
    -0.11
    æİ´
    -0.08
    ä¸Ģçķª
    -0.08
    nds
    -0.08
    uada
    -0.08
    inus
    -0.08
    _starts
    -0.08
    nda
    -0.08
    åĬłä¸Ĭ
    -0.08
    glass
    -0.08
    POSITIVE LOGITS
    åıªæĺ¯ä¸ºäºĨ
    0.11
    é£İåIJ¹
    0.11
    寻æ±Ĥ
    0.10
    以便
    0.10
    ä¸įéĢĤ
    0.10
    污泥
    0.10
    èĩªå¦Ĥ
    0.09
    çľĭæľĽ
    0.09
     ÑĩÑĤобÑĭ
    0.09
    æīĵäºĨ
    0.09
    Activations Density 0.139%

    No Known Activations