© 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. 10487
    Prev
    Next
    INDEX
    Explanations

    very / much + adjective

    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
    çļij
    -0.21
    REC
    -0.20
    гаÑĢ
    -0.19
     enctype
    -0.18
     Savage
    -0.18
    зи
    -0.18
    ize
    -0.17
    æģ°
    -0.17
    å°ıå·§
    -0.17
    _Desc
    -0.17
    POSITIVE LOGITS
    .Keyword
    0.20
    æ´»ä¸ĭåİ»
    0.20
    æŃī
    0.19
    å¹´çĶ±
    0.19
    jährige
    0.18
    acher
    0.18
    ç¯ĩ
    0.18
    éķ¿éķ¿
    0.17
    尺度
    0.17
    -long
    0.17
    Activations Density 0.008%

    No Known Activations