© 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. 5498
    Prev
    Next
    INDEX
    Explanations

    asset, machinery, equipment, capital

    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©»
    -0.10
    æ³¥
    -0.09
    /effects
    -0.09
    vod
    -0.09
    ä½£
    -0.09
    åĢ¡
    -0.09
    åĩłå®¶
    -0.09
    ä»İä¸ļ
    -0.09
     thù
    -0.08
    åĶ±
    -0.08
    POSITIVE LOGITS
    èµĦ产
    0.13
     asset
    0.13
    å®ŀçī©
    0.13
     assets
    0.12
    设å¤ĩ
    0.12
    åĽºå®ļèµĦ产
    0.11
     equipment
    0.11
    .asset
    0.11
     Assets
    0.11
    assets
    0.11
    Activations Density 0.032%

    No Known Activations