© 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. 30334
    Prev
    Next
    INDEX
    Explanations

    planning to do something

    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
    æĢ¥äºİ
    -0.10
    çĽ¼æľĽ
    -0.10
    èģĮå·¥
    -0.09
    erah
    -0.09
    _fixture
    -0.09
    çi
    -0.09
    åħļå§Ķ书记
    -0.09
    è°Ķ
    -0.09
    AYER
    -0.09
    æĪijè§īå¾Ĺ
    -0.09
    POSITIVE LOGITS
     eventual
    0.09
    ä¼ļæľī
    0.09
     Rid
    0.09
    åľ¨æľªæĿ¥
    0.09
     ÑģкоÑĢо
    0.09
    è¿Ļä¹Īåģļ
    0.08
    æľīä¸įå°ij
    0.08
     sometime
    0.08
    Eventually
    0.08
    AndGet
    0.08
    Activations Density 0.018%

    No Known Activations