© 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. 32720
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions or clauses

    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
    æĸ°æĪ¿
    -0.10
    使ä¹ĭ
    -0.09
    éļĭ
    -0.09
    ä¹ĭ乡
    -0.09
    ç®į
    -0.09
    ä¸ĢåĪĩ
    -0.09
    éo
    -0.09
    é«ĺèĢĥ
    -0.08
    elper
    -0.08
    åĴĮæĬĢæľ¯
    -0.08
    POSITIVE LOGITS
    ost
    0.11
    çľĭå¾ħ
    0.10
    åij¨ä¸Ģ
    0.10
    åģĩæĹ¥
    0.09
    å¼Ĭ
    0.09
    è¿Ļéĥ¨åĪĨ
    0.08
    åij½åIJį
    0.08
    OST
    0.08
     this
    0.08
    nam
    0.08
    Activations Density 0.173%

    No Known Activations