© 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. 35091
    Prev
    Next
    INDEX
    Explanations

    currency symbols and abbreviations

    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
    æĹłåģ¿
    -0.09
    виÑĤ
    -0.09
    大æĪĺ
    -0.09
    讵
    -0.09
    åĩĿ
    -0.09
    nger
    -0.09
    .Caption
    -0.09
    ãĥŀãĥ³
    -0.08
    èŀįèµĦ
    -0.08
    çݰ身
    -0.08
    POSITIVE LOGITS
    乡
    0.10
    chet
    0.09
    å°ĺ
    0.09
    edin
    0.09
    åħĥå®Ŀ
    0.09
    ÑģÑħ
    0.09
    IPH
    0.09
    éķĢ
    0.08
    éĴ±
    0.08
     flip
    0.08
    Activations Density 0.029%

    No Known Activations