© 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. 16937
    Prev
    Next
    INDEX
    Explanations

    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
    ä¹°åįķ
    -0.10
    çĴĺ
    -0.09
    æŁIJç§įç¨ĭ度
    -0.09
    çķıæĥ§
    -0.09
     SOS
    -0.09
    rip
    -0.09
    æīĢè°ĵ
    -0.09
    èĢģçĪ·
    -0.09
    жа
    -0.09
    beit
    -0.09
    POSITIVE LOGITS
    表æĥħ
    0.09
    \x
    0.09
    认åı¯
    0.08
    转载
    0.08
    quests
    0.08
    æĶ¿æ²»
    0.08
    ä¼Łå¤§
    0.08
    修补
    0.08
    èŁ¹
    0.07
    ex
    0.07
    Activations Density 0.435%

    No Known Activations