© 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. 37963
    Prev
    Next
    INDEX
    Explanations

    early detection and treatment

    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
    æŶæŶ
    -0.10
    åīįæľŁ
    -0.10
    tes
    -0.09
    InstanceState
    -0.09
    éĤ£æł·çļĦ
    -0.09
    æ³¥
    -0.09
    ä¸ŃéĢĶ
    -0.09
    æijĨ
    -0.09
    æıIJåīį
    -0.09
    çĶ¬
    -0.09
    POSITIVE LOGITS
    æīĢæľīæĿĥ
    0.09
    iator
    0.09
    olon
    0.09
    à¹Ģà¸Īà¸Ń
    0.08
    ãĥŃãĥ¼
    0.08
    allon
    0.08
    -seeking
    0.08
    .cleanup
    0.08
    _TODO
    0.08
    æīĩ
    0.08
    Activations Density 0.109%

    No Known Activations