© 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. 15118
    Prev
    Next
    INDEX
    Explanations

    casings and abbreviations like N.W.2d

    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
    ksi
    -0.20
    æħ¢æħ¢çļĦ
    -0.19
    heading
    -0.19
    åī¡
    -0.19
     donate
    -0.19
     aiming
    -0.19
    ofi
    -0.19
    etal
    -0.18
    æŃ¹
    -0.18
    çŀĦåĩĨ
    -0.18
    POSITIVE LOGITS
     há»ĵi
    0.20
    Circular
    0.20
    æĮij
    0.19
    äºĶåĽĽ
    0.19
     GENERATED
    0.19
    ä»£è¡¨åĽ¢
    0.19
    å°±è¿Ļä¹Ī
    0.19
    å½ĵäºĭ
    0.19
    è¯ļå®ŀ
    0.19
    marshall
    0.19
    Activations Density 0.050%

    No Known Activations