© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37205
    Prev
    Next
    INDEX
    Explanations

    asking for patience or understanding

    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
    olt
    -0.09
    bat
    -0.09
    ä¿ĺ
    -0.08
    ought
    -0.08
    _pad
    -0.08
    pon
    -0.08
    èĬ±äºĨ
    -0.08
    æŀľ
    -0.08
    ero
    -0.08
    åĮį
    -0.08
    POSITIVE LOGITS
    积æŀģéħįåIJĪ
    0.10
    ä¸į便
    0.10
    çIJĨ解åĴĮ
    0.09
    æµģåĬ¨æĢ§
    0.08
    æģķ
    0.08
    åŁºå±Ĥ
    0.08
    mute
    0.08
    çIJĨ解
    0.08
    æ¼Ĩ
    0.08
    移æ°ij
    0.08
    Activations Density 0.006%

    No Known Activations