© 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. 21501
    Prev
    Next
    INDEX
    Explanations

    python, C, machine learning

    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
    æŃĮè¯į
    -0.09
    çıłä¸īè§Ĵ
    -0.09
     Boca
    -0.08
     guild
    -0.08
    olon
    -0.08
    quares
    -0.08
    寿
    -0.08
    ä½İä½į
    -0.08
    kest
    -0.08
    åĩij
    -0.08
    POSITIVE LOGITS
    è¡·
    0.12
    绡
    0.11
    æįħ
    0.10
    ä¸Ģè¡Į
    0.10
    åĨħç½®
    0.10
    èĪŀ
    0.09
     Admission
    0.09
     Mei
    0.09
    egot
    0.09
    æķķ
    0.09
    Activations Density 0.284%

    No Known Activations