© 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. 3247
    Prev
    Next
    INDEX
    Explanations

    subject to license

    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
    æ¯Ķéĩį
    -0.24
    ungle
    -0.23
    é¤ħ
    -0.22
    indows
    -0.22
     inexperienced
    -0.22
     (>
    -0.21
    为主çļĦ
    -0.21
    anim
    -0.21
     prim
    -0.21
    prim
    -0.21
    POSITIVE LOGITS
    è°¨
    0.27
     copyrighted
    0.27
    å¦Ĥæľī
    0.25
     NOR
    0.24
    åĩŃ
    0.23
    ï¸ı
    0.23
    ç¬ĶèĢħ
    0.23
    转载
    0.22
    koa
    0.22
    copyright
    0.22
    Activations Density 0.001%

    No Known Activations