© 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. 14427
    Prev
    Next
    INDEX
    Explanations

    cohort study

    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
    FRING
    -0.21
    åĥ¹
    -0.20
    .execution
    -0.20
    ä»·ä½į
    -0.20
    iec
    -0.19
    æ¯Ķäºļ
    -0.19
    åľºéĿ¢
    -0.19
    arus
    -0.19
    Ñģад
    -0.18
    æĪijçľĭ
    -0.18
    POSITIVE LOGITS
    å¹´é¾Ħ
    0.24
    å±ħæ°ij
    0.24
    æķ°æį®
    0.23
    家åºŃ
    0.23
     longitud
    0.22
    modifiable
    0.22
    åģ¥åº·çļĦ
    0.22
    人群ä¸Ń
    0.22
     domic
    0.22
    çłĶ究
    0.21
    Activations Density 0.447%

    No Known Activations