© 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. 34723
    Prev
    Next
    INDEX
    Explanations

    is/are followed by verb/adjective

    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
    æ¯ķç«Łæĺ¯
    -0.10
    ese
    -0.10
    iga
    -0.09
    ceed
    -0.09
    isi
    -0.08
    å¥ļ
    -0.08
    ÑģоÑģ
    -0.08
    endum
    -0.08
    pel
    -0.08
    jets
    -0.08
    POSITIVE LOGITS
    çĵł
    0.10
    大åıij
    0.09
    赧
    0.08
    模èĮĥ
    0.08
    åıijçĶµ
    0.08
     возд
    0.08
     Matth
    0.08
    ãģ¤ãģı
    0.08
    é²ľèĬ±
    0.08
    èĦĶ
    0.08
    Activations Density 0.162%

    No Known Activations