© 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. 63632
    Prev
    Next
    INDEX
    Explanations

    energy efficient homes

    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
    è¿IJåĬ¿
    -0.10
    èĪµ
    -0.09
    çıº
    -0.09
    éĺħ
    -0.09
    ny
    -0.08
    ynam
    -0.08
    å®īæĬļ
    -0.08
    çªģåıij
    -0.08
    æ°´æĻ¶
    -0.08
    å°±è¿ij
    -0.08
    POSITIVE LOGITS
    èĬĤèĥ½
    0.13
    éĽĨæĪIJ
    0.10
    ÑĢажа
    0.10
     homes
    0.10
    èĦ±
    0.10
    èĥ½èĢĹ
    0.10
    å¯Ĩå°ģ
    0.10
    ä¿Ŀ温
    0.10
    èĬĤ
    0.09
    CAPE
    0.09
    Activations Density 0.036%

    No Known Activations