© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51392
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
    ATUS
    -0.09
    马ä¸Ĭå°±
    -0.09
    yla
    -0.09
    ÑģÑĭл
    -0.09
    åĻ
    -0.09
    å½»
    -0.09
     swallow
    -0.09
    /goto
    -0.09
    IDER
    -0.08
    itary
    -0.08
    POSITIVE LOGITS
    æIJĢ
    0.08
    æĬļæij¸
    0.08
    ä¹Ŀ大
    0.08
    羣å®ŀæĢ§
    0.08
    ä¸įæĸŃåľ°
    0.08
    entially
    0.08
    åĬ¼
    0.08
    ine
    0.08
    èĩ´è¾ŀ
    0.08
    advert
    0.08
    Activations Density 0.024%

    No Known Activations