© 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. 8147
    Prev
    Next
    INDEX
    Explanations

    facts and figures

    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
    åģļ个
    -0.10
    深交
    -0.10
    idad
    -0.09
    åıįæŃ£
    -0.09
    SelectedItem
    -0.08
    auer
    -0.08
    inks
    -0.08
    _classification
    -0.08
     Ferdinand
    -0.08
    erer
    -0.08
    POSITIVE LOGITS
    oring
    0.16
    ories
    0.11
    heet
    0.11
    ored
    0.10
     facts
    0.10
    heets
    0.10
    æŁĦ
    0.10
    amax
    0.09
    itious
    0.09
     regime
    0.09
    Activations Density 0.029%

    No Known Activations