© 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. 8605
    Prev
    Next
    INDEX
    Explanations

    torn, ripped, or separated

    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
    verted
    -0.10
     perman
    -0.09
    æѤåĪ»
    -0.09
    мел
    -0.09
    èĩªå·±åĸľæ¬¢
    -0.09
    æ°ijæĶ¿å±Ģ
    -0.08
    æ²±
    -0.08
     bbc
    -0.08
    onom
    -0.08
    .annotate
    -0.08
    POSITIVE LOGITS
    ander
    0.10
    绶
    0.09
    -eyed
    0.09
    angi
    0.09
    alley
    0.09
    اÙĤ
    0.09
    èªī
    0.08
    侬
    0.08
    éĹ¾
    0.08
    æľīä¸ĢçĤ¹
    0.08
    Activations Density 0.003%

    No Known Activations