© 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. 14428
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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
    aus
    -0.18
    uler
    -0.16
    uel
    -0.16
    END
    -0.16
    unks
    -0.15
    itionally
    -0.15
    edly
    -0.15
    USTER
    -0.15
    åŀł
    -0.15
    het
    -0.15
    POSITIVE LOGITS
    acity
    0.17
    ebra
    0.17
    subclass
    0.16
    eters
    0.16
    enschaft
    0.16
    æ´µ
    0.16
    缤纷
    0.15
    isex
    0.15
    ç¿©
    0.15
     обÑĢазом
    0.15
    Activations Density 0.160%

    No Known Activations