© 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. 62806
    Prev
    Next
    INDEX
    Explanations

    browse online

    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
    èµĦæºIJåħ±äº«
    -0.10
    itud
    -0.09
    ities
    -0.09
    ement
    -0.09
    ç¾¹
    -0.09
    ago
    -0.09
    PageRoute
    -0.08
    hou
    -0.08
    uate
    -0.08
     Orchard
    -0.08
    POSITIVE LOGITS
    ê°Ŀ
    0.11
    ä¸įæ¸ħ
    0.11
     اÙĦØ¥ÙĨترÙĨت
    0.10
    icz
    0.10
    ocale
    0.10
    å¼ĢæĿ¥
    0.09
    OrCreate
    0.09
    anel
    0.08
    áŀı
    0.08
    اÙĬ
    0.08
    Activations Density 0.041%

    No Known Activations