© 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. 3329
    Prev
    Next
    INDEX
    Explanations

    professor or chair positions and roles

    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
    åħ¨åĽ½åIJĦåľ°
    -0.24
    缴æİ¥
    -0.24
    æİ¥çĿĢ
    -0.23
    è¾Ĩ车
    -0.23
    ç¥Ĺ
    -0.23
    gar
    -0.23
    .untracked
    -0.23
     дейÑģÑĤв
    -0.22
    Hit
    -0.22
    åı¯éĿłçļĦ
    -0.22
    POSITIVE LOGITS
    ç§ij室
    0.25
     rotational
    0.24
     candidacy
    0.24
     Chapman
    0.24
     Neu
    0.24
     Juda
    0.24
     Procedures
    0.23
     neu
    0.23
     Teaching
    0.23
    æľ¬ç§ij
    0.23
    Activations Density 0.012%

    No Known Activations