© 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. 4318
    Prev
    Next
    INDEX
    Explanations

    Category: living people

    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
    æĬĴ
    -0.09
    åĩºåı°äºĨ
    -0.09
    ãģĻãģ¹
    -0.08
    常åĬ¡åī¯
    -0.08
    åĩĮ
    -0.08
    åĪ¶å®ļäºĨ
    -0.08
    çļĦéģĵçIJĨ
    -0.08
     comb
    -0.08
     .
    -0.08
    éĶĭ
    -0.08
    POSITIVE LOGITS
    缯
    0.09
     redirects
    0.09
    纹
    0.08
    à¹ģหล
    0.08
    fuse
    0.08
    רצ
    0.08
    èĭ±è¯Ń
    0.08
    à¸Ħà¸Ń
    0.08
    çĿ£åĬŀ
    0.08
    ä¸Ĭæµ·è¯ģåĪ¸
    0.08
    Activations Density 1.263%

    No Known Activations