© 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. 2151
    Prev
    Next
    INDEX
    Explanations

    especially pleasing or disturbing news

    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
    å«
    -0.09
    åĪģ
    -0.09
     gó
    -0.08
    ä»ħä¾Ľ
    -0.08
    好ä¸į好
    -0.08
    èijĽ
    -0.08
    å®Įç¾İçļĦ
    -0.08
     heck
    -0.08
    è¿ĩ硬
    -0.08
     Rubin
    -0.08
    POSITIVE LOGITS
    欣æħ°
    0.18
    åºĨ幸
    0.13
    æĦŁåĪ°
    0.12
    令人
    0.12
    ä¸įç¦ģ
    0.12
     glad
    0.11
    çĿĢå®ŀ
    0.11
    欣åĸľ
    0.10
    æĤ²åĵĢ
    0.10
    称ä¹ĭ
    0.10
    Activations Density 0.122%

    No Known Activations