© 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. 52923
    Prev
    Next
    INDEX
    Explanations

    subject to terms or license

    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
    è´¯
    -0.11
    è¿ĻéĩĮéĿ¢
    -0.10
    allis
    -0.10
     Gazette
    -0.08
    ä¹ł
    -0.08
    èĢ»
    -0.08
    貫
    -0.08
    л
    -0.08
    cept
    -0.08
    è¿Ļåħ¶ä¸Ń
    -0.08
    POSITIVE LOGITS
    éŃĶ鬼
    0.10
    æģ¶éŃĶ
    0.09
    è¦ģä¹Ī
    0.09
    ä¸īåĪĨ
    0.08
    _HOT
    0.08
    æīĢå±ŀ
    0.08
    åIJĥçļĦ
    0.08
    ndl
    0.08
    astery
    0.08
    æľºåĬ¨
    0.08
    Activations Density 0.075%

    No Known Activations