© 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. 56387
    Prev
    Next
    INDEX
    Explanations

    components of a system

    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
    nü
    -0.10
    chai
    -0.10
    æĪĹ
    -0.10
    ä¸ĢåĪĻ
    -0.10
    åĿ³
    -0.09
    .onCreate
    -0.09
    SSF
    -0.09
    ABILITY
    -0.09
    å¹»
    -0.09
    ATIONAL
    -0.09
    POSITIVE LOGITS
    ç»ĦæĪIJéĥ¨åĪĨ
    0.13
    ç»Ħ件
    0.11
    ä¾ĽåºĶåķĨ
    0.11
    çݯèĬĤ
    0.11
     components
    0.11
    ç»ĦæĪIJ
    0.11
    éĥ¨ä»¶
    0.10
    ç»Ħè£ħ
    0.10
    èĦ±èIJ½
    0.09
    éħįå¥Ĺ
    0.09
    Activations Density 0.406%

    No Known Activations