© 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. 26469
    Prev
    Next
    INDEX
    Explanations

    LANGUAGE, enable, OPTIONS, infinite, criticised, Port

    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
    京津åĨĢ
    -0.09
    idd
    -0.09
    踪
    -0.08
    ç¼ĵ
    -0.08
    å°ı康
    -0.08
    å½°
    -0.08
    羡
    -0.08
    .jsp
    -0.08
    æ°ijåĬŀ
    -0.08
    ANGO
    -0.08
    POSITIVE LOGITS
    .hs
    0.12
     Haskell
    0.10
    aco
    0.09
     GHC
    0.09
    askell
    0.09
    çĿĩ
    0.09
    æݬ
    0.09
    /*@
    0.09
    æĶ¹æŃ£
    0.08
    å³Ĵ
    0.08
    Activations Density 0.208%

    No Known Activations