© 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. 30719
    Prev
    Next
    INDEX
    Explanations

    gas purchase contracts

    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
    haar
    -0.10
    æį¡
    -0.10
    æ±Łä¸ľ
    -0.09
    åįķ车
    -0.09
    æ·¹
    -0.09
    สรร
    -0.09
    isode
    -0.09
    åı¬åĶ¤
    -0.09
    åij¼åĶ¤
    -0.09
    å¿Ĺ强
    -0.09
    POSITIVE LOGITS
    åĿĤ
    0.10
     Midwest
    0.09
    å¯IJ
    0.09
    天çĦ¶æ°Ķ
    0.09
     Horn
    0.08
     tap
    0.08
    ä¸ĭ游
    0.08
    газ
    0.08
    éĿ
    0.08
    ATED
    0.08
    Activations Density 0.063%

    No Known Activations