© 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. 34392
    Prev
    Next
    INDEX
    Explanations

    financial concepts and entities

    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
    éĻª
    -0.11
    é¢Ĺ
    -0.09
    itesse
    -0.09
    åī¥
    -0.09
    è¯ī
    -0.08
    åħij
    -0.08
    resco
    -0.08
    åĪ»
    -0.08
     demonstr
    -0.08
    èħ°éĥ¨
    -0.08
    POSITIVE LOGITS
     basics
    0.10
    orr
    0.09
     concepts
    0.09
    properties
    0.09
    æݥ触åĪ°
    0.09
     properties
    0.09
    è§Ĥ念
    0.08
     slander
    0.08
    åĴĮå°ļ
    0.08
    ws
    0.08
    Activations Density 0.241%

    No Known Activations