© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3212
    Prev
    Next
    INDEX
    Explanations

    forms shapes or structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    å³°åĢ¼
    -0.26
     amen
    -0.25
    åĩĨåħ¥
    -0.24
     residual
    -0.23
    æĥ°
    -0.23
    åĽłç´ł
    -0.23
     Briggs
    -0.23
     ÑĦакÑĤоÑĢ
    -0.23
     Psychological
    -0.23
    æ·»åĬłåīĤ
    -0.23
    POSITIVE LOGITS
    å½¢çĬ¶
    0.33
     shape
    0.32
    å¤ĸå½¢
    0.30
     flattened
    0.29
     cylindrical
    0.28
    éĢłåŀĭ
    0.28
     necklace
    0.27
    ç´§åĩij
    0.27
     structure
    0.27
     cylinders
    0.27
    Activations Density 0.029%

    No Known Activations