© 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. 12703
    Prev
    Next
    INDEX
    Explanations

    introduction to scientific investigation

    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
    é²ij
    -0.20
    鸬
    -0.19
    ings
    -0.18
    Cb
    -0.18
    座ä½į
    -0.18
    -toast
    -0.18
    æݸ
    -0.18
    omen
    -0.17
    ä¸Ĭå¹´åIJĮæľŁ
    -0.17
    çºłéĶĻ
    -0.17
    POSITIVE LOGITS
    ðŁĮµ
    0.23
    tes
    0.22
     desert
    0.22
    å£ģ
    0.21
     Mexican
    0.21
    æ¦ĨæŀĹ
    0.21
    ä¸įåIJĥ
    0.20
     Desert
    0.20
    hone
    0.20
    çĺł
    0.19
    Activations Density 0.012%

    No Known Activations