© 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. 10787
    Prev
    Next
    INDEX
    Explanations

    months and financial instruments

    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
    åıįè¿ĩæĿ¥
    -0.09
    å¿ł
    -0.08
    åĬ¡
    -0.08
    etine
    -0.08
    IRD
    -0.08
     retro
    -0.08
    iker
    -0.08
    åĽ´
    -0.08
    è¾ĵ
    -0.08
     Kin
    -0.08
    POSITIVE LOGITS
     futures
    0.11
    交æĺĵå¹³åı°
    0.10
    utures
    0.09
    主åĬĽ
    0.09
    广æĴŃçĶµè§Ĩ
    0.09
    桶
    0.09
    åı¯çĶ¨äºİ
    0.09
    emain
    0.09
    ä¸Ģè¾Ĩ
    0.09
     Futures
    0.09
    Activations Density 0.080%

    No Known Activations