© 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. 9554
    Prev
    Next
    INDEX
    Explanations

    rotary powered cutting and grinding tools

    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
    åħ¬åŃIJ
    -0.09
    /feed
    -0.09
    主åĬ¨æĢ§
    -0.09
    èĥĥåı£
    -0.09
    æĭ¢
    -0.08
    ìŀ¥ìĿĦ
    -0.08
    olated
    -0.08
    apos
    -0.08
    ãģ®ãģĤãĤĭ
    -0.08
    æĹłç¼ĺ
    -0.08
    POSITIVE LOGITS
    å·¢
    0.10
    çªĿ
    0.10
    缤
    0.09
    çĵ·çłĸ
    0.09
     Harbor
    0.09
    thane
    0.09
    纪念
    0.08
    æĮĤéĴ©
    0.08
    GraphNode
    0.08
    çĢ
    0.08
    Activations Density 0.115%

    No Known Activations