© 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. 27795
    Prev
    Next
    INDEX
    Explanations

    tools and fasteners

    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
    ä¸Ģçľĭ
    -0.10
    åķĨ人
    -0.10
    æĿĢ
    -0.09
    æŃ¼
    -0.09
    Interop
    -0.09
    é³ı
    -0.09
    å¨Ħ
    -0.09
    asher
    -0.09
    æĬĸ
    -0.09
    æ´ŀå¯Ł
    -0.09
    POSITIVE LOGITS
    æĭ§
    0.11
    æī³
    0.10
    å·¥åħ·
    0.10
     tools
    0.10
    æīŃ磩
    0.09
     pear
    0.09
     wrench
    0.09
    éļ¾å¾Ĺ
    0.09
    èŀº
    0.08
    å·¥
    0.08
    Activations Density 0.079%

    No Known Activations