© 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. 30407
    Prev
    Next
    INDEX
    Explanations

    cities, Companies, teams, species, players, models

    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
    æŁ´
    -0.09
    éĿŀ常
    -0.08
    Wolf
    -0.08
    onet
    -0.08
    æĽ´å¤ļçļĦæĺ¯
    -0.08
    ptom
    -0.08
    éĥ¨åĪĨåĨħ容
    -0.08
     Hust
    -0.08
    å°±æĺ¯ä¸Ģ个
    -0.08
     Wolf
    -0.08
    POSITIVE LOGITS
    ä¹Łéĥ½
    0.11
    åĪĨåĪ«æĺ¯
    0.11
    è¿Ļåĩł
    0.10
    ä¹ĭä¸Ģ
    0.10
    éĽĨä¸Ńåľ¨
    0.10
    èİ«è¿ĩäºİ
    0.09
    éĥ½åľ¨
    0.09
    ä¸Ģ个个
    0.09
    ones
    0.09
    enan
    0.09
    Activations Density 0.150%

    No Known Activations