© 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. 12526
    Prev
    Next
    INDEX
    Explanations

    se.ic.ingeterysisororirus

    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
    è¿ĩåħ³
    -0.21
    åŀ«
    -0.20
    æ£ĭ
    -0.20
    atak
    -0.20
    aunch
    -0.20
    çIJ°
    -0.20
    apur
    -0.19
     racket
    -0.19
     tennis
    -0.19
    éĻĢ
    -0.19
    POSITIVE LOGITS
    icher
    0.21
    æ¶Īéĺ²
    0.20
    åĪ¶åĨ·
    0.20
    æݨéĶĢ
    0.20
     Excellence
    0.20
    ä¼ĺç¾İ
    0.19
    -backed
    0.19
     Julien
    0.19
    å°ıå§IJå§IJ
    0.18
     abb
    0.18
    Activations Density 0.221%

    No Known Activations