© 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. 3248
    Prev
    Next
    INDEX
    Explanations

    CD, DVD, PDF formats

    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
    bay
    -0.28
    Bay
    -0.25
    ä¸Ģä¸Ŀ
    -0.23
    åīĸ
    -0.23
    union
    -0.22
    æĶ»åħĭ
    -0.22
     Ballet
    -0.21
    çĪ¬ä¸Ĭ
    -0.21
    Bang
    -0.21
     Bay
    -0.21
    POSITIVE LOGITS
     outgoing
    0.31
     Creation
    0.30
    Creation
    0.27
    Maker
    0.27
     creation
    0.27
     Maker
    0.26
    åĪ¶ä½ľ
    0.26
     destinations
    0.25
    æĪIJåŀĭ
    0.24
    è½»æĿ¾
    0.23
    Activations Density 0.038%

    No Known Activations