© 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. 13563
    Prev
    Next
    INDEX
    Explanations

    Service names and locations

    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
    å®ĥçļĦ
    -0.23
     conven
    -0.23
    èĢĮ
    -0.23
    éĤ£ä¹Īå¤ļ
    -0.23
    ped
    -0.22
    ot
    -0.21
     PaÅĦstwo
    -0.21
    è´
    -0.20
    åį´
    -0.20
    æĥ³
    -0.20
    POSITIVE LOGITS
     iNdEx
    0.26
     taxp
    0.23
     fkk
    0.23
    'gc
    0.22
    iana
    0.21
    iéndo
    0.21
    >Please
    0.21
    CodeAt
    0.21
    æݨä»ĭä¼ļ
    0.20
     knull
    0.20
    Activations Density 0.089%

    No Known Activations