© 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. 21351
    Prev
    Next
    INDEX
    Explanations

    multiple sclerosis

    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
    éĻ²
    -0.09
     Yates
    -0.09
    çĿĢçľ¼
    -0.09
    oner
    -0.08
    compat
    -0.08
    vest
    -0.08
    ÙĩÙħ
    -0.08
    itto
    -0.08
    çĿĢéĩį
    -0.08
    èĩ¾
    -0.08
    POSITIVE LOGITS
     sclerosis
    0.21
    -choice
    0.16
    iple
    0.12
     Choice
    0.11
    æĦıä¹īä¸Ĭ
    0.11
    IPLE
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    choice
    0.10
    è¯
    0.10
    clerosis
    0.10
    Activations Density 0.045%

    No Known Activations