© 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. 33069
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs or possessives

    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
    .Shared
    -0.09
     ÑĢай
    -0.09
    è¯Ī
    -0.09
    å¤ļæķ°
    -0.08
    åıijæĮ¥
    -0.08
    åĴļ
    -0.08
    urge
    -0.08
    åĩij
    -0.08
    大å¤ļ
    -0.08
     cá»Ń
    -0.08
    POSITIVE LOGITS
    ä¸įä¼ļåĨį
    0.12
    æĹłè®ºå¦Ĥä½ķ
    0.11
    æĹłæīĢè°ĵ
    0.11
    ãģĵãģĿ
    0.10
    æīįè¡Į
    0.10
    åĸľå¥½
    0.10
    åķ¡
    0.10
    è¿Ļä¹Īåģļ
    0.09
    çĦĸ
    0.09
    åĽ¢åijĺ
    0.09
    Activations Density 0.187%

    No Known Activations