© 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. 14634
    Prev
    Next
    INDEX
    Explanations

    groups 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
    ä¸İåħ¶ä»ĸ
    -0.23
    amu
    -0.21
    æľ¬èº«çļĦ
    -0.20
    åĽ½åĨħå¸Ĥåľº
    -0.19
    agog
    -0.19
    emit
    -0.18
    itra
    -0.18
    aste
    -0.18
    Į¨
    -0.18
     seams
    -0.17
    POSITIVE LOGITS
    åĴĮ个人
    0.26
    è§Ħ模
    0.26
    size
    0.21
     sizes
    0.21
    è¦ı模
    0.21
     size
    0.20
    è§Ħ模æľĢ大
    0.20
     sơ
    0.20
    block
    0.20
     lỼn
    0.19
    Activations Density 0.011%

    No Known Activations