© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10486
    Prev
    Next
    INDEX
    Explanations

    percentage

    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
    Negative Logits
    ity
    -0.24
    hip
    -0.22
    ÑģÑı
    -0.21
    azzi
    -0.19
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.18
    ÑģÑĤÑĥп
    -0.16
    bane
    -0.16
    -out
    -0.16
    ject
    -0.15
    plier
    -0.15
    POSITIVE LOGITS
    å§Ķåī¯ä¹¦è®°
    0.19
    ners
    0.18
    elsius
    0.16
    üs
    0.16
    ï¸ı
    0.16
    以ä¸ĬçļĦ
    0.15
    æ°ijæĶ¿å±Ģ
    0.15
    /'
    0.15
    æł·çļĦ
    0.15
    oller
    0.15
    Activations Density 0.096%

    No Known Activations