© 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. 21660
    Prev
    Next
    INDEX
    Explanations

    combustion chamber, bearings, flow

    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
    èĵī
    -0.10
    è°ħ解
    -0.09
    æ±Ŀ
    -0.09
    åIJł
    -0.08
    çĶŁäºİ
    -0.08
    æĽĿ
    -0.08
    à¸Ńาศ
    -0.08
    åĨ»
    -0.08
    ç§ĭåĨ¬
    -0.08
    çĹ¹
    -0.08
    POSITIVE LOGITS
    åıĹ欢è¿İ
    0.09
    -Sah
    0.09
    京åŁİ
    0.09
    hack
    0.08
    åİŁä»¶
    0.08
    quate
    0.08
     Há»Ļi
    0.08
    åıįè¿ĩæĿ¥
    0.08
    miner
    0.08
    Hack
    0.08
    Activations Density 0.088%

    No Known Activations