© 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. 57813
    Prev
    Next
    INDEX
    Explanations

    proper names ending in ner

    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
    çĦ¶æĺ¯
    -0.11
    odi
    -0.10
    æļĿ
    -0.09
    orate
    -0.09
    osit
    -0.09
    ண
    -0.09
    à¸Ńà¸ģ
    -0.09
    را
    -0.09
    iena
    -0.09
    VERN
    -0.08
    POSITIVE LOGITS
    ê¹IJ
    0.13
    ç¼¥
    0.11
    ully
    0.08
    out
    0.08
    cept
    0.08
    åħĢ
    0.08
     Gren
    0.08
    errupt
    0.08
    ç«Ļèµ·æĿ¥
    0.08
    åĶ¿
    0.08
    Activations Density 0.096%

    No Known Activations