© 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. 49572
    Prev
    Next
    INDEX
    Explanations

    game updates and expansions

    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
     filmy
    -0.09
     mainstream
    -0.09
    æīĭä¸Ń
    -0.09
    åĩºçīĪ社
    -0.08
    anto
    -0.08
    ä½İä¸ĭ
    -0.08
     Ø£ØŃد
    -0.08
    宣è¨Ģ
    -0.08
    第ä¸ī代
    -0.08
    大ä¼ļä¸Ĭ
    -0.08
    POSITIVE LOGITS
    spath
    0.09
    æĿ¥äºĨ
    0.09
    tá
    0.09
    çĽijäºĭ
    0.09
    æĿ¥ä¸´
    0.08
    èĻļæŀĦ
    0.08
    isman
    0.08
    íĮ©
    0.08
     Manit
    0.08
    isex
    0.08
    Activations Density 0.010%

    No Known Activations