© 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. 14950
    Prev
    Next
    INDEX
    Explanations

    any type or remotely

    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
    å·²çĦ¶
    -0.21
    èĢĮæĺ¯
    -0.21
    çĪ·
    -0.20
    ä¹Łå°±
    -0.19
    PTY
    -0.19
    gens
    -0.18
    ä¹Łæ²¡æľī
    -0.18
    奶奶
    -0.18
     except
    -0.17
     presumably
    -0.17
    POSITIVE LOGITS
    ifax
    0.22
     whatsoever
    0.20
    æľīä¸ĢçĤ¹
    0.19
    çĭ®åŃIJ
    0.19
    rophe
    0.19
    iami
    0.18
     faint
    0.17
    ç®IJ
    0.17
    åĿĩåı¯
    0.17
    obsolete
    0.17
    Activations Density 0.052%

    No Known Activations