© 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. 6448
    Prev
    Next
    INDEX
    Explanations

    Tampa Bay

    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
    èĩ¾
    -0.10
    太ä¹ħ
    -0.09
    åĨįéĢł
    -0.09
    enant
    -0.09
    ieux
    -0.09
    æ¶Īè´¹åįĩ级
    -0.08
    åħļæĢ»æĶ¯
    -0.08
     Ñĩа
    -0.08
    ä¸ĺ
    -0.08
    .gs
    -0.08
    POSITIVE LOGITS
    认è¯Ĩ
    0.09
    t
    0.09
    æĴ¼
    0.09
    åĸĻ
    0.09
    æ»ī
    0.08
     Waters
    0.08
     Trudeau
    0.08
    ching
    0.08
    äº
    0.08
    ä¸Ģ线
    0.08
    Activations Density 0.001%

    No Known Activations