© 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. 49677
    Prev
    Next
    INDEX
    Explanations

    bot variations + technical context

    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
    onna
    -0.11
    ses
    -0.10
    rians
    -0.09
    ãģĺ
    -0.09
    oire
    -0.09
    å¸ĪèĮĥ大åѦ
    -0.09
    otte
    -0.08
    å°ıæľĭåıĭ
    -0.08
    æľīä¸Ģ次
    -0.08
    tte
    -0.08
    POSITIVE LOGITS
    swana
    0.12
    anical
    0.12
    itude
    0.11
    ivet
    0.11
    folio
    0.11
    enheim
    0.10
    çĺ¾
    0.09
    anic
    0.09
    chaft
    0.09
    ivated
    0.09
    Activations Density 0.029%

    No Known Activations