© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22275
    Prev
    Next
    INDEX
    Explanations

    which introduces a descriptor

    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
    ãģĤãĤĬãģ¾ãģĻãģĮ
    -0.10
     Smy
    -0.09
    ä¸ĢæĶ¯
    -0.09
     Scar
    -0.08
    丰æĶ¶
    -0.08
    èĨı
    -0.08
    èĦIJ
    -0.08
    establish
    -0.08
    ä¸ĩæĪ·
    -0.08
    æµİ
    -0.08
    POSITIVE LOGITS
    ĵį
    0.10
    _DETECT
    0.09
    abet
    0.09
    çļĦæĥħ绪
    0.09
    æľį
    0.09
    æīįæĺ¯
    0.09
    æħİ
    0.09
     ÑĢеÑĪа
    0.09
    ä¿Ŀ
    0.08
    çļĦå¿ĥæĥħ
    0.08
    Activations Density 0.150%

    No Known Activations