© 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. 49531
    Prev
    Next
    INDEX
    Explanations

    farewell, goodbye, bye

    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
    åĩĢåĮĸ
    -0.10
    æİ©
    -0.10
    .combine
    -0.10
    å¼Ģå¹ķå¼ı
    -0.09
    -eyed
    -0.09
     lá»ĩ
    -0.09
    çĨĦ
    -0.09
    幸ç¦ıæĦŁ
    -0.09
    _MSK
    -0.09
    _BACKEND
    -0.09
    POSITIVE LOGITS
    æĤłæĤł
    0.09
    alto
    0.09
    ather
    0.08
    éģ
    0.08
    é¤ĺ
    0.08
    ðŁijĭ
    0.08
    aug
    0.08
    çģĮ
    0.08
    icia
    0.08
    lich
    0.08
    Activations Density 0.013%

    No Known Activations