© 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. 31206
    Prev
    Next
    INDEX
    Explanations

    player names

    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
    prd
    -0.09
     penet
    -0.08
    kat
    -0.08
    æij¸
    -0.08
    usting
    -0.08
     lod
    -0.08
    é¢ĩ为
    -0.08
    ALLY
    -0.08
    泡泡
    -0.08
    ä¸Ģéģĵ
    -0.08
    POSITIVE LOGITS
    çļĦåĪ°æĿ¥
    0.11
     whom
    0.09
    çľ¼çIJĥ
    0.09
    ä»ĸ认为
    0.09
    èIJ½æĪ·
    0.09
    å¼ķè¿Ľ
    0.09
     whose
    0.09
    åı¯çĶ¨
    0.09
    age
    0.08
    çļĦåIJĪä½ľ
    0.08
    Activations Density 0.052%

    No Known Activations