© 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. 12772
    Prev
    Next
    INDEX
    Explanations

    racial, fix, working, it

    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
     danmark
    -0.32
     köln
    -0.27
     limburg
    -0.27
     milfs
    -0.26
     nuru
    -0.25
     münchen
    -0.25
     taxp
    -0.24
    _ComCallableWrapper
    -0.24
     geschichten
    -0.24
     rotterdam
    -0.23
    POSITIVE LOGITS
     it
    0.28
     they
    0.26
     namely
    0.26
     either
    0.26
     both
    0.25
    either
    0.24
     but
    0.24
     up
    0.24
    ,,
    0.24
    it
    0.24
    Activations Density 0.101%

    No Known Activations