© 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. 12162
    Prev
    Next
    INDEX
    Explanations

    've followed by past participle

    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
    son
    -0.19
    sson
    -0.19
    иÑĤеÑĤ
    -0.18
    /or
    -0.18
    ity
    -0.18
    phans
    -0.18
    orem
    -0.17
    ors
    -0.17
    paging
    -0.17
    çłĿ
    -0.17
    POSITIVE LOGITS
     been
    0.25
     gotta
    0.23
    edo
    0.19
     got
    0.19
    å¤ļ次
    0.18
     PaÅĦstwo
    0.18
    æıIJ
    0.17
    ä¹İ
    0.17
     gonna
    0.17
    Got
    0.16
    Activations Density 0.226%

    No Known Activations