© 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. 57995
    Prev
    Next
    INDEX
    Explanations

    walking aids and locomotion impairment

    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
    æ¥Ŀ
    -0.10
    èĨĽ
    -0.08
    ç»ıå¼Ģ
    -0.08
    å°ijéĩı
    -0.08
    èĮ¸
    -0.08
    iones
    -0.08
    åij¨äºĮ
    -0.08
    áŀļ
    -0.08
    çĶ©
    -0.08
    西äºļ
    -0.08
    POSITIVE LOGITS
    æĭĦ
    0.10
    çīµå¼ķ
    0.10
    æĭIJ
    0.10
    ãģ£
    0.10
    è·Ľ
    0.09
    eking
    0.09
    oran
    0.09
     traction
    0.08
    _walk
    0.08
    èĬ®
    0.08
    Activations Density 0.070%

    No Known Activations