© 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. 9868
    Prev
    Next
    INDEX
    Explanations

    margin and padding

    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
    åķĨ
    -0.08
    åĩ¶
    -0.08
    ersen
    -0.08
    eler
    -0.08
    ä¸įéĢļ
    -0.08
    è¡¥åĬ©
    -0.08
    é£ŁåłĤ
    -0.08
    读åIJİ
    -0.08
    æıIJéĢŁ
    -0.08
     Conce
    -0.07
    POSITIVE LOGITS
    è£ķ
    0.12
     margins
    0.12
     EdgeInsets
    0.12
    _margin
    0.10
    Margins
    0.10
    èį¡
    0.10
     Margin
    0.10
     margin
    0.10
    é¢ĦçķĻ
    0.10
     безопаÑģноÑģÑĤи
    0.10
    Activations Density 0.099%

    No Known Activations