© 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. 2311
    Prev
    Next
    INDEX
    Explanations

    Kosovo, Province, Montenegro, ubital, undra

    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
    ег
    -0.09
    çĩ¥
    -0.09
    åĪĹ
    -0.09
    å¤ĸè´¸
    -0.08
     tá»ij
    -0.08
    åijĬ
    -0.08
    instr
    -0.08
     паÑĢÑĤ
    -0.08
    éĺģ
    -0.08
    itter
    -0.08
    POSITIVE LOGITS
    é»ijé¾Ļ
    0.10
    ä¸Ģ侧
    0.09
    ä¹ĸä¹ĸ
    0.09
    å½ĵå±Ģ
    0.09
    _DISPATCH
    0.09
    ÙĦÙĬÙħ
    0.08
    ãģ¤ãĤĤãĤĬ
    0.08
    undra
    0.08
    ä¸įåŃĺåľ¨
    0.08
     Affero
    0.08
    Activations Density 0.054%

    No Known Activations