© 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. 10942
    Prev
    Next
    INDEX
    Explanations

    prepositions and relation words

    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
    ä¸įå®Į
    -0.10
    æĢ»æľī
    -0.09
    åĴĮåıijå±ķ
    -0.09
    ä¸Ńæľī
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    PIP
    -0.09
    鼳
    -0.09
    çļĦä¸ĢéĿ¢
    -0.08
    åħ¬ç¤º
    -0.08
    ä¸įæĪIJ
    -0.08
    POSITIVE LOGITS
    为ä½ķ
    0.11
    ils
    0.09
    æѤåĪ»
    0.08
    поÑĩ
    0.08
    å¦Ĥä½ķ
    0.08
    reen
    0.08
    为ä»Ģä¹Ī
    0.08
    å±ĢéĿ¢
    0.08
    æĮ¤
    0.08
     ÑģпоÑģоб
    0.08
    Activations Density 0.004%

    No Known Activations