© 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. 28119
    Prev
    Next
    INDEX
    Explanations

    lentiscus, astaxanthin, sempervirens

    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
    ervas
    -0.10
     sorte
    -0.09
    erv
    -0.09
     chests
    -0.09
     Ec
    -0.08
    æİ¥åıĹéĩĩ访
    -0.08
     Merc
    -0.08
    lector
    -0.08
    uell
    -0.08
    ä¸Ģ线
    -0.08
    POSITIVE LOGITS
    åĽ¢åijĺ
    0.11
    èİ«åIJį
    0.10
    าà¸ĩ
    0.10
    人身
    0.10
    otle
    0.10
    çŀ³
    0.09
    çī©ä»¶
    0.09
    möglichkeiten
    0.09
    人群ä¸Ń
    0.09
    .rad
    0.08
    Activations Density 0.002%

    No Known Activations