© 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. 12364
    Prev
    Next
    INDEX
    Explanations

    overhead light fixtures and ceiling surfaces

    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
    åĩłæŃ¥
    -0.22
    cott
    -0.20
    æĭľ
    -0.20
    å²Ľå±¿
    -0.20
    åģ·
    -0.20
    海岸
    -0.19
    escort
    -0.19
    çĦIJ
    -0.19
    èĥŃ
    -0.19
    åľ°åĿĹ
    -0.18
    POSITIVE LOGITS
     overhead
    0.30
    æĤ¬æĮĤ
    0.26
    天èĬ±æĿ¿
    0.23
    åĿł
    0.22
     hangs
    0.21
    åIJĬ顶
    0.21
    头顶
    0.21
    åŀĤ
    0.20
    æĶ¾å®½
    0.20
    纶
    0.20
    Activations Density 0.024%

    No Known Activations