© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10388
    Prev
    Next
    INDEX
    Explanations

    courtyard or courthouse

    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
    天涯
    -0.09
    常åĬ¡åī¯
    -0.08
    ÌĢ
    -0.08
    æ´ģçĻ½
    -0.08
    çģ«å±±
    -0.08
    urvey
    -0.08
    hazi
    -0.08
    ched
    -0.08
    社ä¼ļåĮĸ
    -0.08
    åħ¶æ¬¡
    -0.08
    POSITIVE LOGITS
    ãģĹãģ¾ãģĦ
    0.11
    åĬ²
    0.09
    ³
    0.09
    ums
    0.09
    ipt
    0.09
     legit
    0.09
    ãģĵãģĿ
    0.09
    ÙĬÙĨا
    0.08
    é¡¿
    0.08
     wsp
    0.08
    Activations Density 0.006%

    No Known Activations