© 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. 52549
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     же
    -0.10
    çĥŃ度
    -0.09
    æľīæĿ¡ä»¶
    -0.09
    åŃij
    -0.08
    èķī
    -0.08
     hoop
    -0.08
     Milan
    -0.08
    æ·±åħ¥æİ¨è¿Ľ
    -0.08
    jas
    -0.08
    巴士
    -0.08
    POSITIVE LOGITS
    æĤ²
    0.09
     hòa
    0.09
    éĻįä½İæĪIJæľ¬
    0.09
    设计æĸ¹æ¡Ī
    0.09
    äºİæѤ
    0.08
    커
    0.08
    abet
    0.08
    suming
    0.08
    ERM
    0.08
    è¿Ļç§įæĥħåĨµ
    0.08
    Activations Density 0.503%

    No Known Activations