© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51620
    Prev
    Next
    INDEX
    Explanations

    myofascial release, trauma, formula, palpation

    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
    åľ¨è¿ĩ渡
    -0.11
    è¾IJ
    -0.10
    åľ¨è¿ĩæ¸¡æľŁ
    -0.10
    ÑĦÑĤ
    -0.09
    è¿ĩ渡
    -0.09
    åĦĺ
    -0.09
    _GAP
    -0.09
    大åݦ
    -0.09
     ÑįлекÑĤÑĢо
    -0.09
    åı¶çīĩ
    -0.08
    POSITIVE LOGITS
    积èĵĦ
    0.10
     fasc
    0.09
    çĺĢ
    0.09
    åĽº
    0.09
    æĮīæij©
    0.09
    åį¸
    0.08
    otten
    0.08
    æĢħ
    0.08
    æĪ¿åŃIJ
    0.08
     bÄĥng
    0.08
    Activations Density 0.055%

    No Known Activations