© 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. 3392
    Prev
    Next
    INDEX
    Explanations

    Purdue University

    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
    istic
    -0.24
    à¥į
    -0.23
    ibility
    -0.21
    çīĩåŃIJ
    -0.21
    ended
    -0.21
     converse
    -0.21
    ularity
    -0.20
    ning
    -0.20
    ilarity
    -0.19
    çĺ¾
    -0.19
    POSITIVE LOGITS
    åŀĦ
    0.23
    管家
    0.21
    zan
    0.21
    ly
    0.21
    le
    0.21
    lever
    0.20
    /Area
    0.20
     farms
    0.20
    åĨľæ°ij
    0.20
     Herc
    0.19
    Activations Density 0.002%

    No Known Activations