© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21041
    Prev
    Next
    INDEX
    Explanations

    uns followed by suffix

    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
    åĬ¨èį¡
    -0.10
    ãģ¾ãģĻãģĮ
    -0.09
    _SECURE
    -0.09
    Ø«ÙĪر
    -0.09
    erd
    -0.09
    izards
    -0.08
    IVATE
    -0.08
    hall
    -0.08
    gang
    -0.08
    stown
    -0.08
    POSITIVE LOGITS
    iben
    0.09
    axon
    0.09
    ingleton
    0.09
     hữu
    0.08
    flake
    0.08
    ights
    0.08
    atel
    0.08
    ä½İè°ĥ
    0.08
    illum
    0.08
     overs
    0.08
    Activations Density 0.034%

    No Known Activations