© 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. 17061
    Prev
    Next
    INDEX
    Explanations

    library

    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
    çĻ¾å§ĵ
    -0.22
    åĪ°è¿ĻéĩĮ
    -0.21
    è®®åijĺ
    -0.21
    бав
    -0.20
    éĤ»éĩĮ
    -0.20
    模ç³Ĭ
    -0.19
    使èĢħ
    -0.19
    æ£Ģå¯Łå®ĺ
    -0.19
    á»įc
    -0.18
    ä»ħ代表
    -0.18
    POSITIVE LOGITS
    ä¸Ģ线
    0.20
     staff
    0.20
    ä¸įèĥ½åĨį
    0.19
    ä½ĵåĪ¶
    0.19
    _TestCase
    0.19
     sourceMappingURL
    0.19
    çIJ´
    0.19
    褥
    0.18
    ]interface
    0.18
     metab
    0.18
    Activations Density 0.011%

    No Known Activations