© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    press release

    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
    Not in Any Lists

    No Comments

    Negative Logits
     uniquely
    -0.24
    StatusBar
    -0.22
     equally
    -0.22
    ä¼Łå¤§å¤įåħ´
    -0.22
     ours
    -0.22
    åıĺäºĨ
    -0.21
    å½ĵä¹ĭ
    -0.21
    ssf
    -0.21
    SSF
    -0.21
    纪å§Ķ书记
    -0.21
    POSITIVE LOGITS
    æĩ¿
    0.24
    ikel
    0.24
    转载
    0.23
    诽
    0.23
     Companies
    0.23
    speech
    0.23
    -commercial
    0.22
    edin
    0.22
    yme
    0.22
     scares
    0.22
    Activations Density 0.002%

    No Known Activations