© 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. 33692
    Prev
    Next
    INDEX
    Explanations

    save money

    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
    hoe
    -0.09
    jsc
    -0.08
     اÙĦÙĪاØŃد
    -0.08
     parted
    -0.08
    æļĤ
    -0.08
    ç½ijç»ľä¼łæĴŃ
    -0.08
    强æľīåĬĽ
    -0.08
    嵯
    -0.08
    .getOwnProperty
    -0.08
    æľīæĿ¡ä»¶
    -0.08
    POSITIVE LOGITS
    èĬĤçľģ
    0.24
    èĬĤ约
    0.20
     savings
    0.19
     saves
    0.16
     saving
    0.15
     Savings
    0.15
    çľģéĴ±
    0.14
    avings
    0.14
    -save
    0.14
     save
    0.14
    Activations Density 0.058%

    No Known Activations