© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20282
    Prev
    Next
    INDEX
    Explanations

    sports teams and players

    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
    çij°
    -0.10
    京
    -0.10
    è°Ħ
    -0.09
    ubs
    -0.09
    å¼ķåħ¥
    -0.09
    åľ¨äº¬
    -0.09
    iras
    -0.09
    onné
    -0.09
    翱
    -0.09
    defgroup
    -0.08
    POSITIVE LOGITS
    çĻ½æ²Ļ
    0.09
    ä¸įçķĻ
    0.09
     Yoshi
    0.09
    ode
    0.08
    ä¸įä¸Ģå®ļ
    0.08
    bos
    0.08
    éļ¹
    0.08
    纵
    0.08
    hart
    0.08
    å·«
    0.08
    Activations Density 0.031%

    No Known Activations