© 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. 39910
    Prev
    Next
    INDEX
    Explanations

    verbs followed by 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
    oha
    -0.09
    é¢Ħ计
    -0.09
    çĬĢ
    -0.09
     ÑĢейÑĤинг
    -0.09
     hart
    -0.09
    -Sah
    -0.08
     تÙħاÙħ
    -0.08
    PropertyParams
    -0.08
     semen
    -0.08
    åı«å£°
    -0.08
    POSITIVE LOGITS
    好åIJĹ
    0.09
    .Messages
    0.09
    sg
    0.08
    æĹłå¥Ī
    0.08
    Poster
    0.08
    æĥħåĨµæĿ¥çľĭ
    0.08
    樾
    0.08
    å°Ĭ
    0.08
    /her
    0.08
    çī¹æľīçļĦ
    0.08
    Activations Density 0.189%

    No Known Activations