© 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. 22099
    Prev
    Next
    INDEX
    Explanations

    amed or assisted living

    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
    kaar
    -0.10
    peria
    -0.10
    ä½İä¼°
    -0.09
     verr
    -0.09
    è¡
    -0.09
    æĵº
    -0.09
    ası
    -0.08
    ÑģоÑĤ
    -0.08
    tics
    -0.08
     Sar
    -0.08
    POSITIVE LOGITS
    åľ¨ä¸ĢæĹģ
    0.10
    èĿĩ
    0.09
    y
    0.09
     ctr
    0.09
    pole
    0.08
     Eden
    0.08
    å·²åľ¨
    0.08
    æĤ²
    0.08
    åīįåı°
    0.08
    amp
    0.08
    Activations Density 0.006%

    No Known Activations