© 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. 5065
    Prev
    Next
    INDEX
    Explanations

    transactional or role-based contexts

    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
    oom
    -0.09
    æľ¬æľŁ
    -0.09
     %#
    -0.09
    äºŃ
    -0.08
     caucus
    -0.08
    assing
    -0.08
    çŃīå½¢å¼ı
    -0.08
    mith
    -0.08
    rets
    -0.08
    éķĶ
    -0.08
    POSITIVE LOGITS
    æŁIJç§į
    0.10
    çļ±
    0.10
    Disposable
    0.10
    çķĪ
    0.09
     disposable
    0.09
    æ¶ĪèĢĹ
    0.09
    åķĨåĵģ
    0.09
    åĨĮ
    0.09
    åĻĹ
    0.09
     Decoration
    0.09
    Activations Density 0.053%

    No Known Activations