© 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. 22818
    Prev
    Next
    INDEX
    Explanations

    Rhodes, Greek islands

    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
    éĵŁ
    -0.10
     ÐŁÑĢе
    -0.09
    é¹Į
    -0.09
    âm
    -0.09
    .BL
    -0.09
    梯éĺŁ
    -0.08
    绶
    -0.08
    åŀĦ
    -0.08
    éľĸ
    -0.08
    åĿ¨
    -0.08
    POSITIVE LOGITS
    åįģéĩĮ
    0.12
    å¸ĮèħĬ
    0.11
     Greek
    0.09
     Hansen
    0.09
    èį¯åºĹ
    0.09
    æĻĥ
    0.09
    Greek
    0.08
    ODEV
    0.08
    å®ł
    0.08
    hic
    0.08
    Activations Density 0.057%

    No Known Activations