© 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. 50406
    Prev
    Next
    INDEX
    Explanations

    ball retrieval

    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
    à®´
    -0.10
    æīĭåĬ¿
    -0.09
    oku
    -0.09
    oli
    -0.09
    зд
    -0.09
     dispens
    -0.09
     iceberg
    -0.09
    è¿ĩæĪ·
    -0.09
    abet
    -0.09
    blo
    -0.09
    POSITIVE LOGITS
    æİīèIJ½
    0.13
    丢
    0.11
    èIJ½
    0.10
    æķ£
    0.10
    éģĹ
    0.10
    æį¡
    0.10
    åı°éĺ¶
    0.09
    åĽĽå¤Ħ
    0.09
    åľ¨åľ°ä¸Ĭ
    0.09
    ãģĤãģ¨
    0.09
    Activations Density 0.056%

    No Known Activations