© 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. 62665
    Prev
    Next
    INDEX
    Explanations

    Baldwin or malondialdehyde

    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
    halb
    -0.11
    ests
    -0.11
     деп
    -0.09
    ually
    -0.09
    æĪijè§īå¾Ĺ
    -0.09
    Cls
    -0.09
    ure
    -0.08
    éľ²å¤©
    -0.08
    osition
    -0.08
    urement
    -0.08
    POSITIVE LOGITS
    ry
    0.10
    çĥ¨
    0.10
    _epi
    0.10
    ĶĦ
    0.10
    ãģĤãĤĭ
    0.10
    åĩłåĪĨ
    0.09
    stä
    0.09
    \TestCase
    0.09
    .getLine
    0.09
    å°ı康社ä¼ļ
    0.08
    Activations Density 0.003%

    No Known Activations