© 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. 18264
    Prev
    Next
    INDEX
    Explanations

    price and quantity indicators

    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
    æĭŁ
    -0.12
    пÑĥ
    -0.10
    æĵ¬
    -0.09
     Autonomous
    -0.09
    å°¤åħ¶
    -0.09
    cctor
    -0.09
     Emmanuel
    -0.09
    íĶĦë¡ľê·¸
    -0.08
    è¿Ļåĩł
    -0.08
    åĿij
    -0.08
    POSITIVE LOGITS
    ä¸Ģåıª
    0.09
    ä¸ĢåIJ¬
    0.08
    åĪ°åľº
    0.08
    æĸ°éĹ»ç½ij
    0.08
     воÑģ
    0.08
    èĬľ
    0.08
    笺
    0.08
    ofil
    0.07
    PerPage
    0.07
    .resume
    0.07
    Activations Density 0.039%

    No Known Activations