© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21069
    Prev
    Next
    INDEX
    Explanations

    at least one

    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
    çī¹æ´¾
    -0.11
    è±ģ
    -0.09
    æ¸ħæ°´
    -0.09
    åłĤ
    -0.09
    èĮ¨
    -0.08
    åı¯çĶ¨
    -0.08
    udios
    -0.08
    æĻ°
    -0.08
    åĩ¿
    -0.08
    ondo
    -0.08
    POSITIVE LOGITS
    ieved
    0.09
    楼ä¸Ĭ
    0.09
    ugin
    0.09
     Ferguson
    0.08
    ãĤĭãģĵãģ¨ãģ¯
    0.08
    éĢĭ
    0.08
    жи
    0.08
    æĪijçĽ¸ä¿¡
    0.08
     press
    0.08
    quoted
    0.08
    Activations Density 0.039%

    No Known Activations