© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52473
    Prev
    Next
    INDEX
    Explanations

    assets and liability

    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
    é¡¿
    -0.09
     кÑĢай
    -0.09
    ForResult
    -0.09
    æĢ§å¼º
    -0.09
    åĨ²åĬ¨
    -0.09
    cot
    -0.09
    é¼»
    -0.09
    æµį
    -0.08
    æ¢Ĺ
    -0.08
    _IMP
    -0.08
    POSITIVE LOGITS
     assets
    0.18
    èµĦ产
    0.16
    assets
    0.16
     Assets
    0.16
    Assets
    0.14
    æĢ»èµĦ产
    0.12
    .assets
    0.12
    /assets
    0.11
    -assets
    0.11
    è´ŁåĢº
    0.11
    Activations Density 0.042%

    No Known Activations