© 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. 55987
    Prev
    Next
    INDEX
    Explanations

    banking and finance

    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
    /ion
    -0.11
    andard
    -0.10
     Toro
    -0.09
    ality
    -0.09
    HING
    -0.09
    bies
    -0.09
    imit
    -0.09
    ascript
    -0.09
    .TO
    -0.08
    SION
    -0.08
    POSITIVE LOGITS
    æĸ¹éĿ¢çļĦ
    0.10
    ä¸į便
    0.10
    aze
    0.10
    åľ°å¸¦
    0.09
    åĪ¶åº¦æĶ¹éĿ©
    0.09
     Burnett
    0.08
    ound
    0.08
    ayer
    0.08
    çĿĢå®ŀ
    0.08
    zell
    0.08
    Activations Density 0.004%

    No Known Activations