© 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. 12903
    Prev
    Next
    INDEX
    Explanations

    or /or

    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
    phans
    -0.25
    ients
    -0.24
    izontal
    -0.21
    ç«Łæĺ¯
    -0.21
    å¹²èĦĨ
    -0.19
    ä¸ĢæĶ¯
    -0.19
     equivalent
    -0.19
    opa
    -0.19
    说æĺ¯
    -0.18
    acles
    -0.18
    POSITIVE LOGITS
    /or
    0.48
     or
    0.33
    æĪĸèĢħ
    0.33
    æĪĸ
    0.32
     или
    0.30
     æĪĸ
    0.29
    /OR
    0.29
    æĪĸæĺ¯
    0.27
     Ø£ÙĪ
    0.27
    ê±°ëĤĺ
    0.26
    Activations Density 0.303%

    No Known Activations