© 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. 22721
    Prev
    Next
    INDEX
    Explanations

    uro- prefixes, Neuro- prefixes

    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
    åĽŀäºĭ
    -0.12
    cheid
    -0.08
    nis
    -0.08
    ãĤĤãģĨ
    -0.08
    æİĩ
    -0.08
    ij
    -0.08
     tard
    -0.08
    åŃIJéĩĮ
    -0.08
     raid
    -0.08
    RY
    -0.08
    POSITIVE LOGITS
    浪
    0.10
    phones
    0.09
    ëį°
    0.09
    леж
    0.09
    à¹Ĥà¸Ł
    0.09
    eing
    0.09
    tant
    0.09
    ÙĩÙĪ
    0.08
    liest
    0.08
    cape
    0.08
    Activations Density 0.078%

    No Known Activations