© 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. 3150
    Prev
    Next
    INDEX
    Explanations

    live differently

    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
    带走
    -0.10
    ingly
    -0.09
    éĽī
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.09
    ä¸ĢèĦļ
    -0.08
    åĩ¡äºĭ
    -0.08
    REMOTE
    -0.08
    ä¸Ģè¡Į
    -0.08
    oppers
    -0.08
    elige
    -0.08
    POSITIVE LOGITS
    æĸ¹å¼ı
    0.12
    对å¾ħ
    0.12
     manner
    0.12
    æĸ¹å¼ıè¿Ľè¡Į
    0.11
    çľĭå¾ħ
    0.11
    é£İæł¼
    0.10
    ÑĢин
    0.10
    è¯łéĩĬ
    0.09
    èĮĦ
    0.09
    çļĦæĸ¹å¼ı
    0.09
    Activations Density 0.108%

    No Known Activations