© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49067
    Prev
    Next
    INDEX
    Explanations

    ideas and exchange

    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
    orus
    -0.10
    levels
    -0.08
    éĺĸ
    -0.08
    epam
    -0.08
    åijĬ
    -0.08
    ayas
    -0.08
    éĻį
    -0.08
    лив
    -0.08
    åĿIJçĿĢ
    -0.07
     dug
    -0.07
    POSITIVE LOGITS
     ideas
    0.24
    ideas
    0.22
     Ideas
    0.21
    æĢĿæĥ³
    0.20
    æĥ³æ³ķ
    0.19
    idea
    0.15
     idea
    0.15
    念头
    0.15
    主æĦı
    0.15
     concepts
    0.14
    Activations Density 0.076%

    No Known Activations