© 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. 34116
    Prev
    Next
    INDEX
    Explanations

    a [person, group, or place]

    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
    çĻ¾å§ĵ
    -0.09
     Salisbury
    -0.09
    家åĽŃ
    -0.09
    ilst
    -0.09
    çī¡
    -0.08
    æĺİæľĹ
    -0.08
    åĴĮå°ļ
    -0.08
    æĶ¾çľ¼
    -0.08
     Defensive
    -0.08
    æ°ijæĶ¿
    -0.08
    POSITIVE LOGITS
    TEE
    0.11
    åIJįåı«
    0.09
    otify
    0.09
    anko
    0.09
    ä¸įæĦ¿
    0.08
    onde
    0.08
    翻身
    0.08
     unspecified
    0.08
    oks
    0.08
    ÅĤa
    0.08
    Activations Density 0.124%

    No Known Activations