© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10653
    Prev
    Next
    INDEX
    Explanations

    couples, friends, or teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    鸱
    -0.22
     clip
    -0.21
    _CLIP
    -0.20
    _ENUM
    -0.19
    è¿Ļ家ä¼Ļ
    -0.19
    åĻ«
    -0.18
    ä¸ĢåĪĢ
    -0.18
    çłº
    -0.18
    dependence
    -0.18
     обÑĢаÑī
    -0.18
    POSITIVE LOGITS
    对ä»ĸ们
    0.25
    åĽĽä¸ª
    0.23
    æīĢæľī人
    0.22
    ä¸Ģç»Ħ
    0.21
    åĽĽä½į
    0.20
    让ä»ĸ们
    0.20
     theirs
    0.20
    åį¬
    0.19
    /rfc
    0.19
    æŀĦæĪIJ
    0.19
    Activations Density 0.145%

    No Known Activations