© 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. 16039
    Prev
    Next
    INDEX
    Explanations

    prior art

    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
    è¿Ļ件äºĭæĥħ
    -0.20
     tight
    -0.17
     edit
    -0.17
     pure
    -0.17
     Edit
    -0.17
    itia
    -0.17
    ำ
    -0.17
    **
    -0.17
    æĭ¿çĿĢ
    -0.17
    çľĭä¸Ģçľĭ
    -0.16
    POSITIVE LOGITS
    gó
    0.18
    rimon
    0.18
    inar
    0.18
    amon
    0.17
    rien
    0.17
    yor
    0.16
    好å¥ĩ
    0.16
    çīµæĮĤ
    0.16
    æļĦ
    0.16
    	AM
    0.16
    Activations Density 0.884%

    No Known Activations