© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37549
    Prev
    Next
    INDEX
    Explanations

    successful

    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
    éĨ
    -0.10
    го
    -0.10
    å¾Īæľī
    -0.09
    æĥħåĨµè¿Ľè¡Į
    -0.09
    çī¹æ®ĬæĥħåĨµ
    -0.09
     гоÑĤов
    -0.08
    æķĻç¨ĭ
    -0.08
    ä¼ĺåĮĸ
    -0.08
    çĥŃçĪ±
    -0.08
    AINER
    -0.08
    POSITIVE LOGITS
    æįķ
    0.12
    .Success
    0.11
    ç§ĺè¯Ģ
    0.10
    çļĦæĪIJåĬŁ
    0.10
    æĪIJåĬŁ
    0.10
    æĪIJåĬŁçļĦ
    0.10
    (success
    0.10
    åŀļ
    0.09
     SUCCESS
    0.09
    omi
    0.09
    Activations Density 0.129%

    No Known Activations