© 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. 11953
    Prev
    Next
    INDEX
    Explanations

    joint motion, exercise, medicine, static, manual, oscill, isotonic

    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
    è´ª
    -0.09
     nhiên
    -0.08
    æķij
    -0.08
    ç»Ī身
    -0.08
     наÑĢ
    -0.08
     háºŃu
    -0.08
    è£Ĥ
    -0.08
     glo
    -0.08
    åIJİå¤ĩ
    -0.08
    walker
    -0.08
    POSITIVE LOGITS
    UCT
    0.11
    PRI
    0.10
    /Foundation
    0.10
    åħ±åIJĮä½ĵ
    0.09
    对æĬĹ
    0.09
    _ISO
    0.09
    _PUSH
    0.09
    械
    0.09
    çļĦåĬĽéĩı
    0.09
    çĪ¹
    0.09
    Activations Density 0.317%

    No Known Activations