© 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. 30884
    Prev
    Next
    INDEX
    Explanations

    lack or thereof

    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
     анг
    -0.10
    æĦıåij³
    -0.10
    ä¸ĭæīĭ
    -0.10
    æļ¹
    -0.09
    京åī§
    -0.09
     panda
    -0.09
    (CONT
    -0.08
    ä¼Ĺ
    -0.08
    éªĬ
    -0.08
    ENDED
    -0.08
    POSITIVE LOGITS
     lack
    0.14
    ä¸İåIJ¦
    0.12
    æ¯Ķäºļ
    0.10
     Lack
    0.10
    缺ä¹ı
    0.10
    å¾Ī好
    0.09
     falta
    0.09
    ä¸įä½³
    0.09
    akt
    0.08
    çĤİ
    0.08
    Activations Density 0.061%

    No Known Activations