© 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. 13572
    Prev
    Next
    INDEX
    Explanations

    free or gratis

    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
    igm
    -0.20
     pac
    -0.20
    orth
    -0.20
    marks
    -0.18
    pty
    -0.18
     writable
    -0.17
    ling
    -0.17
    åĭĭ
    -0.17
    las
    -0.17
    ä¹ĺçĶ¨è½¦
    -0.17
    POSITIVE LOGITS
    åħįè´¹
    0.53
     беÑģплаÑĤно
    0.43
     gratis
    0.40
    æĹłåģ¿
    0.40
    åħįè²»
    0.39
     gratuit
    0.35
    åħ¬çĽĬ
    0.35
     gratuito
    0.35
     kostenlos
    0.33
     free
    0.33
    Activations Density 0.163%

    No Known Activations