© 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. 19511
    Prev
    Next
    INDEX
    Explanations

    staring at

    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
    寻
    -0.10
    好æ¶Īæģ¯
    -0.10
    ç¾ŀ
    -0.09
     вÑģÑİ
    -0.09
    ãĤŃãĥ³
    -0.09
    迹象
    -0.09
    æĺ¨
    -0.09
    åĪ»
    -0.09
    æĸ©èİ·
    -0.09
    ä¹°åĪ°
    -0.09
    POSITIVE LOGITS
    çĽ¯çĿĢ
    0.16
    çŀª
    0.15
    æľĽçĿĢ
    0.13
    çľĭçĿĢ
    0.13
     staring
    0.12
    注è§Ĩ
    0.12
    åijĨ
    0.12
     stare
    0.11
    è§ĤæľĽ
    0.11
    æĢĶ
    0.11
    Activations Density 0.023%

    No Known Activations