© 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. 37665
    Prev
    Next
    INDEX
    Explanations

    `are` followed by verbs 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
    ä¸Ĭæĸ¹
    -0.09
    æľ«
    -0.09
    ilater
    -0.09
    _BP
    -0.08
    梳
    -0.08
    æĺ¯ä¸Ģ项
    -0.08
    ilet
    -0.08
    ACP
    -0.08
     amort
    -0.08
    大家éĥ½
    -0.08
    POSITIVE LOGITS
     themselves
    0.16
    å¾ģ
    0.13
     PaÅĦstwo
    0.12
     Ñģами
    0.11
    sg
    0.11
    ä¸Ģ个个
    0.11
    ingly
    0.11
    åħīæĺİ
    0.10
    æĥ¶
    0.10
    ÅĽmy
    0.10
    Activations Density 0.422%

    No Known Activations