© 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. 22251
    Prev
    Next
    INDEX
    Explanations

    Monitoring hosting routines

    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
     Hao
    -0.08
    æľīå¿ħè¦ģ
    -0.08
    XB
    -0.08
    æºĥ
    -0.08
    oola
    -0.08
    å¼ĢæĿ¥
    -0.08
     emb
    -0.08
    emb
    -0.08
    åľ¨çİ°åľº
    -0.08
    没åħ³ç³»
    -0.08
    POSITIVE LOGITS
    attached
    0.11
    åIJĬ
    0.11
    _checks
    0.09
     attached
    0.09
    ÇIJ
    0.09
    åĮħåIJ«äºĨ
    0.09
    ä¸ĢæĿ¡
    0.09
    ç¼Ĩ
    0.09
    æīĵæĸŃ
    0.09
     LENG
    0.09
    Activations Density 0.071%

    No Known Activations