© 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. 8416
    Prev
    Next
    INDEX
    Explanations

    wounds and healing

    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
    ities
    -0.09
    oney
    -0.09
    ector
    -0.09
    åĽ¢
    -0.09
    çļ¿
    -0.08
    é¢Ĩ导干éĥ¨
    -0.08
     мил
    -0.08
    ãĤĵãģ§ãģĻãģŃ
    -0.08
    å°ijè§ģ
    -0.08
    åľĺ
    -0.08
    POSITIVE LOGITS
    LESS
    0.12
    edly
    0.12
    edList
    0.11
    ful
    0.11
    less
    0.09
    sWith
    0.09
    lessly
    0.09
    Ñħа
    0.09
     inflicted
    0.09
    WithOptions
    0.09
    Activations Density 0.023%

    No Known Activations