© 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. 20529
    Prev
    Next
    INDEX
    Explanations

    Half-Life games

    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
    apel
    -0.08
     Ames
    -0.08
    å¼Ģä¼ļ
    -0.08
    ç¦ıåĪ©
    -0.08
     Lionel
    -0.08
    buffers
    -0.08
    بÙĬØ©
    -0.08
    åIJijãģį
    -0.08
    æijĨ
    -0.08
    åħ¬å¼Ģåıij
    -0.08
    POSITIVE LOGITS
     Ngo
    0.09
     wyÅĽwietl
    0.09
    ä¸įæĸŃå®ĮåĸĦ
    0.09
    æ¨Ł
    0.09
    让çĶ¨æĪ·
    0.09
    SystemService
    0.09
    éĺ²æ°´
    0.09
    麻辣
    0.09
    ä¸īä½įä¸Ģä½ĵ
    0.09
    ä½ĵç³»
    0.09
    Activations Density 0.064%

    No Known Activations