© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56484
    Prev
    Next
    INDEX
    Explanations

    articles in publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    éļĶ
    -0.10
    olate
    -0.08
     Mud
    -0.08
    æ³¥
    -0.08
    fans
    -0.08
    éļĶçĿĢ
    -0.08
    çĬ¯
    -0.08
    æķħäºĭ
    -0.08
    åĿŃ
    -0.08
    ç²Ĺ
    -0.08
    POSITIVE LOGITS
    æľŁåĪĬ
    0.19
    æĿĤå¿Ĺ
    0.19
     magazine
    0.19
     journal
    0.17
     magazines
    0.16
    åĪĬçī©
    0.16
    åij¨åĪĬ
    0.15
     Magazine
    0.15
    æĬ¥çº¸
    0.14
     жÑĥÑĢнал
    0.14
    Activations Density 0.093%

    No Known Activations