© 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. 17137
    Prev
    Next
    INDEX
    Explanations

    tough, rough, hardened, feared

    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
    åı¹æģ¯
    -0.22
    æ¶ķ
    -0.22
    çļĦç¾İ好
    -0.22
    ç¹ģ
    -0.21
    å±ģ
    -0.21
    漫
    -0.20
    entifier
    -0.20
    èĬ±å¼Ģ
    -0.19
    èĮ«èĮ«
    -0.19
    çļĻ
    -0.19
    POSITIVE LOGITS
    硬
    0.24
    -hard
    0.23
     Tough
    0.23
     tough
    0.23
     hardened
    0.23
    对æĬĹ
    0.23
    åĬĽéĩı
    0.22
    æįį
    0.22
    æĬ¤
    0.21
    强硬
    0.21
    Activations Density 0.030%

    No Known Activations