© 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. 51917
    Prev
    Next
    INDEX
    Explanations

    behind the scenes

    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
    çIJ¼
    -0.10
    æļ¨
    -0.09
    éĢ®
    -0.09
     bli
    -0.09
    åĿł
    -0.08
    Dot
    -0.08
    _MODULES
    -0.08
    éĵĹ
    -0.08
    åѦåīįæķĻèĤ²
    -0.08
    åħļçļĦé¢Ĩ导
    -0.08
    POSITIVE LOGITS
    å¹ķåIJİ
    0.22
    èĥĮåIJİ
    0.18
     behind
    0.18
    çļĦèĥĮåIJİ
    0.18
    Behind
    0.17
     Behind
    0.16
    èĥĮåIJİçļĦ
    0.16
    åĨħå¹ķ
    0.13
    æļĹ
    0.13
    é»ĺé»ĺ
    0.13
    Activations Density 0.064%

    No Known Activations