© 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. 48139
    Prev
    Next
    INDEX
    Explanations

    Dodd-Frank, Patriot Act, Affordable Care Act

    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
    çĶŁåij½çļĦ
    -0.09
    classNames
    -0.09
    ä¸įä¸ĭ
    -0.08
    èĦ
    -0.08
    oz
    -0.08
    å¥ij
    -0.08
    éºĴ
    -0.08
    åı¯éĿłçļĦ
    -0.08
     jav
    -0.08
    å¿Ĩ
    -0.08
    POSITIVE LOGITS
    è¿ŀå¤ľ
    0.11
    èµĽ
    0.10
     Spicer
    0.09
     suite
    0.09
    .rm
    0.09
    çĶ
    0.09
    suite
    0.09
    åħ¥çĿ¡
    0.08
     suites
    0.08
    è°ª
    0.08
    Activations Density 0.008%

    No Known Activations