© 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. 14829
    Prev
    Next
    INDEX
    Explanations

    debate and legislative proceedings

    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
    èIJĮ
    -0.22
    èįĩ
    -0.22
     exter
    -0.20
    çĬĦ
    -0.20
    ķĮ
    -0.20
    æ°ijéĹ´
    -0.19
    访
    -0.19
    å´½
    -0.19
    温馨æıIJ示
    -0.19
    讵
    -0.19
    POSITIVE LOGITS
     speeches
    0.22
    æİĴéĺŁ
    0.21
    æİĴ
    0.20
    èĪ
    0.20
    å¸Ń
    0.19
    iola
    0.19
    ubar
    0.18
    миниÑģÑĤ
    0.18
    ldata
    0.18
    edics
    0.18
    Activations Density 0.014%

    No Known Activations