© 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. 14377
    Prev
    Next
    INDEX
    Explanations

    promotional offers, price, material, products, ads

    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
    erness
    -0.21
    shima
    -0.18
    sse
    -0.17
    ennes
    -0.17
     ÙĪاÙĦÙĨ
    -0.16
    uddle
    -0.16
     Chancellor
    -0.16
    tracked
    -0.16
    chants
    -0.15
    íĸ¥
    -0.15
    POSITIVE LOGITS
    æīĭ段
    0.22
    åľ°å¸¦
    0.20
    æĢ§å¼º
    0.19
    æ´»åĬ¨
    0.19
    iliary
    0.19
    æĹ¶æ®µ
    0.18
    æľŁéĹ´
    0.18
    ity
    0.18
    æ±ľ
    0.17
    æīĭæ³ķ
    0.17
    Activations Density 0.004%

    No Known Activations