© 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. 32619
    Prev
    Next
    INDEX
    Explanations

    oil and gas industry terms

    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
    .pix
    -0.09
    念
    -0.09
    ä»»æľŁ
    -0.08
    TERM
    -0.08
    åħī彩
    -0.08
    åĩĮ
    -0.07
    arness
    -0.07
    .inflate
    -0.07
    /dc
    -0.07
    _DC
    -0.07
    POSITIVE LOGITS
    åĭĺæİ¢
    0.18
    å¼Ģéĩĩ
    0.16
    åľ°è´¨
    0.14
    åİŁæ²¹
    0.13
    åĤ¨éĩı
    0.12
    åĮºåĿĹ
    0.12
    éĩĩçŁ¿
    0.12
    æ²¹æ°Ķ
    0.12
    åĭĺæŁ¥
    0.12
    è¿IJèIJ¥åķĨ
    0.10
    Activations Density 0.118%

    No Known Activations