© 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. 14314
    Prev
    Next
    INDEX
    Explanations

    sprint and lance

    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
    åĥļ
    -0.18
    vez
    -0.18
    iley
    -0.18
    çĦ¼ãģį
    -0.17
    ëģĶ
    -0.17
    æIJį害
    -0.16
    塾
    -0.16
    erk
    -0.16
     Stamford
    -0.16
    rd
    -0.16
    POSITIVE LOGITS
    opia
    0.19
    rix
    0.18
    uous
    0.17
    ers
    0.17
    åı¤æĢª
    0.17
    lopedia
    0.16
    ä¿Ŀæ´ģ
    0.16
    eden
    0.16
    ILLED
    0.16
    arel
    0.15
    Activations Density 0.003%

    No Known Activations