© 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. 20132
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    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
    æĬµ
    -0.10
    åĬłä¸Ĭ
    -0.09
    Ùģار
    -0.09
    apos
    -0.09
    ä¸ľæµ·
    -0.08
     lasers
    -0.08
    trl
    -0.08
     Endpoint
    -0.08
    åĶIJ
    -0.08
     tieten
    -0.08
    POSITIVE LOGITS
    纾
    0.11
    çļĦåĬŁæķĪ
    0.09
    çĤİ
    0.08
    妯
    0.08
    ä¸Ńå°ıä¼ģä¸ļ
    0.08
    çĹĪ
    0.08
    Compat
    0.08
    æķıéĶIJ
    0.08
    icho
    0.08
    ä»Ģä¹Īéĥ½
    0.08
    Activations Density 0.157%

    No Known Activations