© 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. 48990
    Prev
    Next
    INDEX
    Explanations

    invention relates to lighting apparatus

    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
    æµģåĩº
    -0.11
    æµģåħ¥
    -0.10
     Block
    -0.09
    BlockSize
    -0.09
    .isOpen
    -0.09
    _SCOPE
    -0.09
    izr
    -0.09
    á»ijc
    -0.09
    åıĤ
    -0.09
    _PORTS
    -0.09
    POSITIVE LOGITS
    çģ¯åħ·
    0.12
    çħ§æĺİ
    0.12
     Lighting
    0.11
    è·¯çģ¯
    0.11
    çģ¯
    0.11
     lighting
    0.10
    çĤ¹äº®
    0.10
    æ¯ĶåĪ©
    0.10
    çĨĦ
    0.09
    çħ§äº®
    0.09
    Activations Density 0.086%

    No Known Activations