© 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. 48616
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by determiners or 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
    VID
    -0.11
    vid
    -0.10
    è´Ŀ
    -0.08
    ç»Ĩç»Ĩ
    -0.08
    殿åłĤ
    -0.08
    allet
    -0.08
     Saud
    -0.08
    ary
    -0.08
     VID
    -0.08
    enco
    -0.08
    POSITIVE LOGITS
    顺
    0.10
    aten
    0.10
    çĸ¾
    0.10
    积æŀģå¼Ģå±ķ
    0.09
    å¹²èĦĨ
    0.09
    ä¸Ģ身
    0.09
    èIJ½åľ¨
    0.08
     Jed
    0.08
    èIJ½åĪ°
    0.08
     Sche
    0.08
    Activations Density 0.058%

    No Known Activations