© 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. 5747
    Prev
    Next
    INDEX
    Explanations

    Italian cities and places

    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
    æ£Ģä¿®
    -0.09
     islands
    -0.09
     island
    -0.09
    æĪijä»¬åľ¨
    -0.09
    åijĺ
    -0.09
    æ²Ķ
    -0.08
    idi
    -0.08
     perennial
    -0.08
    èŀĥèŁ¹
    -0.08
    ents
    -0.08
    POSITIVE LOGITS
    atel
    0.10
    æ¡ī
    0.10
    ç¬ı
    0.10
    æĢ¥
    0.09
    è±¹
    0.09
    egment
    0.09
    éĥ¨åĪĨåľ°åĮº
    0.09
    åįģä¸ĩ
    0.09
    éĻĮ
    0.09
    /apt
    0.08
    Activations Density 0.023%

    No Known Activations