© 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. 15003
    Prev
    Next
    INDEX
    Explanations

    Affordable Care Act, Tax, Q, 1

    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
    icone
    -0.22
    çī©ä»·
    -0.20
    .eng
    -0.19
    å¨ľ
    -0.19
    uae
    -0.19
    riot
    -0.19
    蹬
    -0.18
    èĮ¹
    -0.18
    .uint
    -0.18
    .lab
    -0.18
    POSITIVE LOGITS
    è¾ĵäºĨ
    0.20
    éĻĽ
    0.20
    ä¸įæľį
    0.19
    人群ä¸Ń
    0.19
    _each
    0.18
    éļ¶
    0.18
    çľ¼
    0.18
    аниз
    0.18
    éĶµ
    0.18
    å¦Ĥæŀľä¸į
    0.18
    Activations Density 0.006%

    No Known Activations