© 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. 22005
    Prev
    Next
    INDEX
    Explanations

    been followed by time or status

    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
    ç¾°
    -0.11
    æĢİä¹Īä¼ļ
    -0.11
    以èĩ´
    -0.10
    æ¼¾
    -0.10
    综
    -0.10
    å¢Ģ
    -0.10
    ä¸įèĩ³äºİ
    -0.09
    ODO
    -0.09
    CLR
    -0.09
    ç±´
    -0.09
    POSITIVE LOGITS
    ä¼ı
    0.08
    åĪ³
    0.08
    -op
    0.08
     hab
    0.08
     slopes
    0.08
    amp
    0.08
    èĩ´åĬĽ
    0.08
    åĽ°æī°
    0.08
     ÑģÑĤало
    0.08
     Linden
    0.08
    Activations Density 0.138%

    No Known Activations