© 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. 35410
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions followed by nouns

    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
    åijĬè¯īæĪij
    -0.09
    被æĬĵ
    -0.09
    atham
    -0.08
    è·¯
    -0.08
    å¼ĵ
    -0.08
    Credits
    -0.08
    èĥ¡åŃIJ
    -0.08
    ìĤ¬ìĹħ
    -0.08
     brochure
    -0.08
    åĭī强
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĪĻ
    0.11
    为大家
    0.10
    ä»ĭç»įä¸Ģä¸ĭ
    0.10
    åķIJ
    0.10
    äºĨ解ä¸Ģä¸ĭ
    0.09
    æ¯Ķè¾ĥç®Ģåįķ
    0.09
    大家åĪĨ享
    0.09
    åIJ¬åIJ¬
    0.09
    åı¦ä¸Ģä½į
    0.09
    ä¸Ģç¯ĩ
    0.09
    Activations Density 0.233%

    No Known Activations