© 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. 10976
    Prev
    Next
    INDEX
    Explanations

    indoor air, windows, container, conditioned, summer

    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
    湿
    -0.10
    æ¿ķ
    -0.10
    æ»ĭ润
    -0.10
    踪
    -0.09
     paw
    -0.09
     Merrill
    -0.09
    æ½ľæ°´
    -0.09
    éļĶçĿĢ
    -0.09
    æĥ³è±¡åĬĽ
    -0.09
    å®īåİ¿
    -0.09
    POSITIVE LOGITS
    åĿĿ
    0.09
    åıĮåIJij
    0.09
    Ñĥй
    0.08
    ä¸įåĩº
    0.08
    INY
    0.08
    uum
    0.08
    æݥ管
    0.08
    禺
    0.08
    éħĮ
    0.08
     boil
    0.08
    Activations Density 0.078%

    No Known Activations