© 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. 17734
    Prev
    Next
    INDEX
    Explanations

    theoretical physics and statistics

    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
     пÑĢе
    -0.09
    æķĽ
    -0.09
    hone
    -0.08
    éĢłä»·
    -0.08
    佯
    -0.08
    æ¼³
    -0.08
     rule
    -0.08
    jee
    -0.08
    ider
    -0.07
     simulator
    -0.07
    POSITIVE LOGITS
    пан
    0.10
    ëĭĿ
    0.10
    æ·
    0.10
    .setModel
    0.09
    çĶ¨äººåįķä½į
    0.09
    -leaning
    0.09
    oretical
    0.09
    ALLY
    0.09
    воÑĢ
    0.09
    åĿļå®ŀ
    0.08
    Activations Density 0.060%

    No Known Activations