© 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. 10866
    Prev
    Next
    INDEX
    Explanations

    design / designers

    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
    onga
    -0.10
    è¯Ģ
    -0.10
    åıī
    -0.09
     ÑĢейÑĤинг
    -0.08
    ccion
    -0.08
    ÑĪин
    -0.08
    lopen
    -0.08
    çĹķ
    -0.08
    virt
    -0.08
    ưỡng
    -0.08
    POSITIVE LOGITS
    _design
    0.12
     Design
    0.12
     design
    0.11
    设计
    0.11
    çļĦ设计
    0.11
    design
    0.11
    Design
    0.10
     DESIGN
    0.10
    çĹĶ
    0.10
    è¨Ńè¨Ī
    0.10
    Activations Density 0.237%

    No Known Activations