© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2458
    Prev
    Next
    INDEX
    Explanations

    whether to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ä¸įä½Ĩ
    -0.30
    ä¸įä»ħ
    -0.26
    -away
    -0.24
    VERY
    -0.23
    次
    -0.22
    次è¦ģ
    -0.22
    æľīä¸įå°ij
    -0.22
    èĩ³å°ij
    -0.22
    为äºĨ让
    -0.21
    ä¸įä»ħè¦ģ
    -0.21
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.45
     whether
    0.28
    ä»»ä½ķå½¢å¼ı
    0.28
    æĪIJè´¥
    0.28
    åĬĽè¿ĺæĺ¯
    0.28
    whether
    0.27
    Regardless
    0.27
     whatsoever
    0.27
    Whether
    0.26
    å¤ļä¹Ī
    0.26
    Activations Density 0.035%

    No Known Activations