© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39806
    Prev
    Next
    INDEX
    Explanations

    magnetic stimulation therapy

    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
    hog
    -0.09
    за
    -0.09
    輪
    -0.08
    icher
    -0.08
    ÑĥÑĤÑĮ
    -0.08
    ibo
    -0.08
    åIJIJ
    -0.08
    ìķŀ
    -0.08
    æģ£
    -0.08
    VIS
    -0.08
    POSITIVE LOGITS
    pons
    0.09
     therapy
    0.09
    .dense
    0.09
    夯å®ŀ
    0.09
    好æľĭåıĭ
    0.09
    licit
    0.08
    åįķ身
    0.08
    æ¥Ŀ
    0.08
    atar
    0.08
    é¢Ĩçķ¥
    0.08
    Activations Density 0.192%

    No Known Activations