© 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. 31744
    Prev
    Next
    INDEX
    Explanations

    place names ending in suffixes like "-o", "-u", "-a"

    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
    åĤ¾
    -0.09
    ysi
    -0.09
    -proxy
    -0.09
    ä¸ĬçıŃ
    -0.09
    çĵ£
    -0.08
    ä¸ĬåѦ
    -0.08
    ucks
    -0.08
    èĽĽ
    -0.08
    DEST
    -0.08
    OffsetTable
    -0.08
    POSITIVE LOGITS
    éĺĻ
    0.10
    .cn
    0.09
     Falls
    0.09
    æŶéĹ´åĴĮ
    0.09
    éĺģ
    0.08
    è°Ģ
    0.08
    ç½ķ
    0.08
    马ä¸ģ
    0.08
    canf
    0.08
    htm
    0.08
    Activations Density 0.130%

    No Known Activations