© 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. 17462
    Prev
    Next
    INDEX
    Explanations

    other people or entities

    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
    æĪijèĩªå·±
    -0.09
    ÙĬÙĤ
    -0.08
     bruk
    -0.08
    使æĪij
    -0.08
    ateria
    -0.08
    quer
    -0.08
     materia
    -0.08
     пÑĢинÑı
    -0.08
    åŀĤ
    -0.08
    äºĭåIJİ
    -0.08
    POSITIVE LOGITS
    对æĸ¹
    0.13
    åı¦ä¸ĢåįĬ
    0.12
    å°įæĸ¹
    0.11
    说èĩªå·±
    0.11
    éħįåģ¶
    0.10
    身边çļĦ
    0.10
     اÙĦآخر
    0.10
    赧
    0.10
    对èĩªå·±çļĦ
    0.10
    对éĿ¢
    0.09
    Activations Density 0.096%

    No Known Activations