© 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. 51753
    Prev
    Next
    INDEX
    Explanations

    certified or licensed professionals

    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
    Ctl
    -0.09
    íĻĶ
    -0.09
    Ô
    -0.09
    تس
    -0.08
    itz
    -0.08
    ttl
    -0.08
     доÑģÑĤ
    -0.08
    OLL
    -0.08
    åģ·
    -0.08
     Yük
    -0.08
    POSITIVE LOGITS
    å¹²ä»Ģä¹Ī
    0.11
    åħħå½ĵ
    0.09
    è¡ĮåĬ¨è®¡åĪĴ
    0.09
    ä¸Ķ
    0.08
    æµģæ°´
    0.08
    å¼ĢéŨ
    0.08
    æĿ¥èĩªäºİ
    0.08
    åĪĨ解
    0.08
    éĢIJ
    0.08
    pec
    0.08
    Activations Density 0.039%

    No Known Activations