© 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. 17901
    Prev
    Next
    INDEX
    Explanations

    engine head bolts intake 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
    æ¿Ģ
    -0.09
    æ¬
    -0.09
    åħ¨å¤©
    -0.09
    ä¹ĭ声
    -0.08
     Ler
    -0.08
    æ³ķå®ļ
    -0.08
    çĶ¨éĩı
    -0.08
    uÃŃ
    -0.08
    å²ģæľĪ
    -0.08
    æīĭæĦŁ
    -0.08
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.11
    çļĦæĶ¯æĮģ
    0.10
    Į¨
    0.09
    çīµ
    0.09
    ivent
    0.09
    æ²Ł
    0.09
    帽åŃIJ
    0.09
    èıľé¸Ł
    0.09
    æĭĸ
    0.09
    unte
    0.09
    Activations Density 0.132%

    No Known Activations