© 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. 2075
    Prev
    Next
    INDEX
    Explanations

    East West South North

    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
    OSP
    -0.10
    åIJĮç±»
    -0.10
    ÙĬست
    -0.09
    .Hosting
    -0.09
    çĶļèĩ³æĺ¯
    -0.09
    orro
    -0.09
    åįĩ温
    -0.09
     Offline
    -0.09
    acking
    -0.09
    slash
    -0.09
    POSITIVE LOGITS
    没æľīä»»ä½ķ
    0.08
    ints
    0.08
     Pill
    0.08
    梧
    0.08
    两æĿ¡
    0.07
     deut
    0.07
    æĹłç¼Ŀ
    0.07
    .er
    0.07
    èģĤ
    0.07
     Mont
    0.07
    Activations Density 0.014%

    No Known Activations