© 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. 9599
    Prev
    Next
    INDEX
    Explanations

    magazine 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
    çīĮçħ§
    -0.10
    çİĻ
    -0.09
    åĪ©äºļ
    -0.09
    AccessException
    -0.09
    éĤĪ
    -0.08
    åĦĢ
    -0.08
    仪
    -0.08
    箪
    -0.08
    æĬ¤çħ§
    -0.08
    оÑĦ
    -0.08
    POSITIVE LOGITS
    æľŁåĪĬ
    0.13
     ISSN
    0.13
    åĪĬçī©
    0.13
    åĪĬ
    0.13
    æłı缮
    0.13
    æĿĤå¿Ĺ
    0.12
     Magazine
    0.12
    æ¯ıæľĪ
    0.12
    订éĺħ
    0.12
     magazine
    0.11
    Activations Density 0.192%

    No Known Activations