© 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. 11777
    Prev
    Next
    INDEX
    Explanations

    might express possibility

    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
    hed
    -0.11
    thing
    -0.09
    erro
    -0.09
    itted
    -0.09
    ä¹İ
    -0.09
    æĪijçĽ¸ä¿¡
    -0.09
    erk
    -0.08
    леÑĤ
    -0.08
    à¸ĵ
    -0.08
    emm
    -0.08
    POSITIVE LOGITS
    说æĺ¯
    0.12
    ness
    0.11
    ÙĬ
    0.10
    ãģĹãģı
    0.10
    ily
    0.09
    æł·çļĦ
    0.09
    è¿Ļæł·çļĦè¯Ŀ
    0.09
    iness
    0.09
    icism
    0.09
    NESS
    0.09
    Activations Density 0.036%

    No Known Activations