© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12564
    Prev
    Next
    INDEX
    Explanations

    mix and match images"- "pick and choose my resources"- "combine with other components"- "interchangeable parts"- "combination of factors"- "combine various desirable traits"- "combining a plurality of parts"- "style-mixing technique"

    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
    ä¸Ģä½ĵ
    -0.23
    åĿļå®ļä¸į移
    -0.21
    å¯Ĩ
    -0.20
    atings
    -0.20
    èĤĥ
    -0.19
    arus
    -0.19
    enguins
    -0.18
    .mas
    -0.18
    éĵŃ
    -0.18
    éĸī
    -0.18
    POSITIVE LOGITS
    åIJĦç§į
    0.23
     freely
    0.22
     Freedom
    0.21
    交éĶĻ
    0.21
     pieces
    0.21
     Fab
    0.20
    åIJĮç±»
    0.20
     individual
    0.20
    ä¸ĢäºĽ
    0.19
    åIJĦåįķä½į
    0.19
    Activations Density 0.012%

    No Known Activations