© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13851
    Prev
    Next
    INDEX
    Explanations

    weights on the order of

    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
    sst
    -0.23
    ÑĥÑī
    -0.19
    IPA
    -0.18
    toa
    -0.17
    íĦ¸
    -0.17
    @brief
    -0.16
    说çļĦæĺ¯
    -0.16
    inding
    -0.16
    erm
    -0.16
    UIScreen
    -0.16
    POSITIVE LOGITS
     ‘
    0.21
    ä»ħ次äºİ
    0.19
    ä»Ģä¹Īåij¢
    0.18
    /an
    0.18
    :
    0.18
    æŀģæĺĵ
    0.17
    /service
    0.17
    ï¼ļ
    0.17
     those
    0.17
    åĨ·ç¬ij
    0.17
    Activations Density 0.180%

    No Known Activations