© 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. 22608
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
    owa
    -0.09
    Invoker
    -0.09
    åľ¨æĪij
    -0.08
     sát
    -0.08
    sink
    -0.08
    èĥĮçĿĢ
    -0.08
    Archive
    -0.08
    orate
    -0.08
    æŃ£å¸¸ä½¿çĶ¨
    -0.08
     lamin
    -0.08
    POSITIVE LOGITS
    oze
    0.09
    æݥ触åĪ°
    0.09
    aaS
    0.09
    (PR
    0.09
    å±ķä¼ļ
    0.09
    çĶ³ãģĹ
    0.09
    Bright
    0.09
    å¾ĭ
    0.08
     ÑĢегиÑģÑĤÑĢа
    0.08
    printStats
    0.08
    Activations Density 0.027%

    No Known Activations