© 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. 35280
    Prev
    Next
    INDEX
    Explanations

    East African countries

    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
    å¤Ń
    -0.10
     Places
    -0.09
    èIJ¥éĢł
    -0.09
    alu
    -0.09
    ditor
    -0.08
    æĸ¥
    -0.08
     places
    -0.08
    åĪ©äºİ
    -0.08
    éļ¶å±ŀäºİ
    -0.08
    à¸Ńà¸ĩ
    -0.08
    POSITIVE LOGITS
    æ©IJ
    0.09
    åķĥ
    0.09
    inke
    0.08
    Ìģ
    0.08
     Burb
    0.08
    è¶ħé¢Ŀ
    0.08
    acidad
    0.08
    pur
    0.08
    åı£æ°´
    0.08
    çĺ¿
    0.08
    Activations Density 0.013%

    No Known Activations